EUMMAS A2S Conference, 19-25 Dubai 2023, United Arab Emirates
|
Government Data Catalog Utilization
to Analyze of the Influencing Factors of Drought in Phetchabun Province |
|
|
|
Porntep Saleepan |
|
College of Industrial Technology,
King Mongkut's University of Technology North Bangkok, Bangkok, Thailand |
|
Hathairat Ketmaneechairat |
|
College of Industrial Technology,
King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand. Email : hathairat.k@cit.kmutnb.ac.th |
|
Sopida Tuammee |
|
College of Industrial Technology,
King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand. Email : sopida.t@cit.kmutnb.ac.th |
|
Darinee
Buddeewong |
|
ASEAN Language and Culture Center,
Mukdahan Community College, Mukdahan, Thailand. Email : darinee@mukcc.ac.th |
|
Lakshmikanth HM |
|
Garden City University, Bangalore,
India. |
|
|
|
Abstract The purpose of this research is to study and analyze the influencing
factors of drought in Phetchabun province. This paper used the dataset of
drought problem from the government data catalog of Phetchabun province. The
information system is created to find out a cause of drought. The provincial
governor of Phenchabun province is importance to solve the drought problem
and forward the policy of solving the drought problem at the meeting of the
data governance commit of Phetchabun province. In the commission meeting
resolution on March 17, 2021 approved the preparation of datasets related to
key issues in the region (Pain points). The dataset is collected to solve the
drought problem by integration data with government sector. There are several
factors used to analyze drought problem such as rainfall, irrigated areas and
water sources, groundwater, humidity, soil moisture, land using and drought
statistics. There are 26 datasets in the preliminary government data catalog,
which are used to prepare the visualization dashboard. The results show that
drought is the significant problem and affects to agriculture and economic
system in Phetchabun province. The provincial governor and committee use
data-driven decision making to solve drought problem. |
|
|
|
Keywords drought problem, government data
catalog, influencing factors, Phenchabun province |
|
|
|
JEL classifications R 10 |
1. Introduction
Nowadays, the government sectors and private
sectors are aware of the importance of analyzing and big data utilizing for the
decision-making and operations. The Office of the Civil Service Commission in collaboration with the Ministry of Digital for the
Economy and Society, the human resource development mechanism for the big data utilizing
has been proposed. The target group of this development consists of 3 groups as
follows: 1) The creator and system developer. 2) Analyst group, process and
display results. 3) Data user group, workgroups. The implement of government's
big data project can be divided into 3 tasks: 1. Working on creating and
maintaining big data information systems. 2. Data analysis and 3. Bringing the information
to use for the decision making (Government Big Data Analysis Framework, 2020)
The analyzing
and displaying of big data, in the paper proposed case study of drought problem
and effect in Phetchabun Province. The provincial governor of Phenchabun
province is importance to solve the drought problem and forward the policy of
solving the drought problem at the meeting of the data governance commit of
Phetchabun province. At the meeting of the Phetchabun Provincial Statistics
Committee No. 1/2021 on March 17, 2021, it was resolved to approve the
preparation of a dataset which related to the key issues in the area (Pain
Point). Phetchabun Province Drought Solution is at risk of drought since most
of the people of the province are mainly engaged in agriculture which still
relies mainly on natural water. Drought is a problem caused by natural
fluctuations coupled with human action affecting the shortage of water for
agriculture. (Requirements for Dataset Analysis for Key Issues, 2022)
In the Phetchabun
Province Annual Government Action Plan, Year Budget 2022, Volume 2, Project No.
25 Activities: Promote and link marketing of safe/organic agricultural
products, processed agriculture and related products. There are the important
agricultural products: such as mangoes, tamarinds, ginger, corn, sugarcane,
vegetables, medicinal plants, etc. And there are the agricultural products that
have been registered as commodities, geographical indication (Geographical
Indication: GI). Moreover, Phetchabun sweet tamarind from Khao Farm Leum Puea,
Phetchabun raising the level of agricultural products to meet the standards of
organic / safe agriculture products such as vegetables, fruits, herbs that are
not food, rice and cereal for household consumption and commercial development.
There are group of farmers in Phetchabun Province who have established
agricultural production plots, namely, 78 large plots, the Center for
Agricultural Product Production Efficiency (CAD) and a network of 219 centers,
1,479 community enterprises, 86 Smart Farmer prototypes and 46 Young Smart
Farmer prototypes.
It is
absolutely necessary to solve or prevent drought problems that occur or may
occur along with finding suitable measures and technologies to bring more land
to use. Including the restoration of forest areas. Especially the watershed
forest area. It increases the potential of the area to accumulate water in the
soil and groundwater planting perennials to add moisture to the dry land area.
Therefore, the researcher has taken the dataset from the government data
accounting to the system in Case Study of Phetchabun Province, the problem of
drought analyzed in order to use the data obtained to study the factors causing
the drought. Prepared in the form of diagrams, graphs and charts (Data
Visualization) and Prescriptive analytics to support the decision-making in
solving drought problems of Phetchabun Province.
2. Related Works
In the last
decades, climate change is regarded as one of the biggest challenges to the
earth because it’s causes and aggravates serious natural hazards including rain
storm-floods, forest fire, tsunami, droughts and many others. The drought
problem has been addressed by many authors because drought has a devastating
effect on the ecology as a potential hydro-meteorological disaster. Due to
extensive impacts of drought in past decades at regional and global scales
leads to improved capability to cope with drought. Thus, drought prediction
plays a key role in drought early warning to mitigate its impacts. At present,
there are a lot of researches on drought forecasting in many countries. In 2020, Han and Singh reviewed
forecasting methods for drought and tree mortality under global warming. This research examines
causative mechanisms for drought and tree mortality, and synthesizes
stochastic, statistical, dynamical, and hybrid statistical-dynamical drought
forecasting models as well as theoretical, empirical, and mechanistic tree
mortality forecasting models. The results from this research demonstrate that
some of the statistical drought forecasting models, which have nonlinear and
nonstationary natures, can be merged with dynamical models to compensate for
their lack of stochastic structure in order to improve forecasting skills.
Afterward, Fung, et al. proposed the improved SVR machine learning models for
predicting the standardized precipitation evapotranspiration indices (SPEI)
with a lead time of one month to minimize potential drought impact on oil palm
plantations at the downstream of Langat River Basin, Malaysia, which has a
tropical climate pattern. However, the potential of developing drought
prediction models over Pakistan using three state-of-the-art Machine Learning
(ML) techniques; Support Vector Machine (SVM), Artificial Neural Network (ANN)
and k-Nearest Neighbour (KNN) was investigated by Khan et al. (2020) which
based on the Standardized Precipitation and Evapotranspiration Index (SPEI). In
2021, Sundararajan, et al. proposed a contemporary review on drought modeling
Using Machine Learning Approaches. They found that the data-driven modelling
for forecasting the metrological time series prediction is becoming more
powerful and flexible with computational intelligence techniques which include
singular vector machines (SVM), support vector regression, random forest,
decision tree, logistic regression, Naive Bayes, linear
regression, gradient boosting tree, k-nearest neighbours (KNN), the adaptive neuro-fuzzy inference system, the feed-forward neural networks,
Markovian chain, Bayesian network, hidden Markov models, and
autoregressive moving averages, evolutionary algorithms, deep learning and many more. Furthermore, several researchers have been established more than 100 drought indices.
Some
applications of satellite data are presented in Mishra, et al. (2021) and
Mokhtari and Akhoondzadeh (2021).
Mishra, et al. (2021) analyzed the extent of drought in the Rajasthan
state of India using vegetation condition index and standardized precipitation
index. This study reconfirms that the use of RS technique for drought risk
assessment is reliable based on the results obtained in this study. Mokhtari
and Akhoondzadeh (2021) described data fusion and machine learning algorithms
for Drought forecasting using satellite data. The modeling of the NDVI index
monthly was performed by using TRMM rainfall data, SMOS satellite soil
moisture, MODIS land surface temperature, snow cover, evapotranspiration with
machine learning algorithms such as SVR algorithm, ANN algorithm, DT algorithm and RF
algorithm. The ANN algorithm has provided higher accuracy than the other three
algorithms.
In recent
years, data mining has been addressed by several successful applications for
drought prediction. For example, Mohammed, et al. (2022) applies data mining
for agricultural and hydrological drought prediction in the eastern
Mediterranean which has the main goals is to capture agricultural and
hydrological drought trends by using the Standardized Precipitation Index (SPI)
and to assess the applicability of four ML algorithms (bagging (BG), random
subspace (RSS), random tree (RT), and random forest (RF)) in predicting drought
events based on SPI-3 and SPI-12. The output could be helping decision-makers
with drought mitigation plans by using the new four machine learning
algorithms. Furthermore, several researchers have studied an artificial neural
network in drought prediction; for example, Dikshit, et al. (2022) provided a
comprehensive review of the various neural networks that have been
traditionally used to forecast droughts in various parts of the world. They
examine the most popular and often used neural network-based models and how
these have improved their understanding of drought forecasting.
Finally, the
machine learning model, drought index and country are used in drought
forecasting as shown in Table I.
Table 1
The machine learning model, drought index and country are used in drought
forecasting.
|
Model Used |
Drought Index |
Country |
|
ANN |
SPI, NADI,
ARID, NDVI, VCI, NDWI, WSVI, NDDI, SWSI |
India,
Australia, United States, Ethiopia, Iran, Kenya |
|
ANFIS, Fuzzy
Logic |
PMDI, SPI |
United
States, Iran, Turkey |
|
SVM |
SPI, SPEI |
Australia,
Pakistan, India |
|
RF |
SPI, SPEI |
Australia,
United States, China |
|
Hybrid Model |
PMDI, SPI,
EDI |
Australia,
United States, Iran, |
|
Deep Learning
Model |
SPI, SPEI |
Australia,
India |
|
ANFIS |
SPI |
Turkey |
|
ANFIS, FFNN |
SPI |
Turkey, Iran |
|
NN |
Palmer |
Iceland |
|
RMSNN, DMSNN,
ARIMA |
Nonlinear
Aggregated |
Australia |
|
ANN, SVR, WN |
SPI |
Ethiopia |
|
ANN, ANFI,
WA-ANN |
SPI |
Iran |
|
MLPANN,
ANFIS, SVM |
SPI |
Iran |
|
MLPNN |
SPEI |
Pakistan |
|
IIS-W-ANN |
SWL |
Australia |
|
DNN |
SPI |
United
Kingdom |
|
DLNM, ANN,
XGB |
ONI, SOI,
PDO, NAO, AMO, IPO |
China |
|
SVR |
SPEI |
China |
|
WFL |
PDSI |
USA |
|
WANN, WFL |
PMDI |
Turkey |
|
BN |
ESP_R, SRI,
SPI, SPEI, PHDI |
Korea, Peninsula |
|
RF |
SPI, SMI,
SPEI |
China, Korea,
Australia |
|
HMM |
SPI |
Korea,
Ethiopia |
|
Semi-Markov |
SDI |
Georgia |
3. Methodology
In this section, the methodology for analysis the
influencing factors of drought problem in Phetchabun Province is described as following.
3.1. Data
Collection and Preparation
The dataset
is download from the government data catalog platform,
which is available at the website: https://gdcatalog.go.th/ or https://phetchabun.gdcatalog.go.th/.
There are 26 datasets in Phetchabun catalog. The list of datasets of Phetchabun
Province as shown in Table 1 and the datasets are divided into 5 group as
follows:
1) Water
demand group (Agricultural sector, Household sector, Industrial sector) Scope
of issue Farmers register, farmer households, target groups register in Khok
Nong Na plot.
2) Water
allocation management (Calculate demand for irrigation water storage) scope of
issues water supply, water sources, artesian wells, provincial basic
information, rainfall, village water supply, zoning of economic crops, farm ponds
(mini ponds), cultivated area, irrigation area.
3) Drought
impacts (consumption, agriculture, environment) Scope of issue Farmers,
households, agricultural products deteriorated soil, dust, inclement weather.
4) Spatial
data (area affected by drought) natural water source space utilization scope of
issues Drought-prone areas, drought-affected areas, recurring drought areas,
dams, reservoirs, artesian wells.
5) Environmental
factors Scope of issue Rainfall amount Characteristics of the area Groundwater
sources, sea level, soil conditions.
Table 2
List of datasets
|
Scope of issues |
Dataset/Data Resource List |
URL |
note |
|
1. Farmer's register,
farmer household |
1.1 Farmer registration |
https://phetchabun.gdcatalog.go.th/dataset/dataset_ |
Phetchabun Provincial
Agricultural Office |
|
1.2 List of target groups
for Khok Nong Na plot |
https://phetchabun.gdcatalog.go.th/dataset/dataset_ |
Phetchabun
Provincial Community
Development Office |
|
|
2. Water supply
consumption |
2.1 Water consumption data |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_01 |
Provincial Water Supply
Authority Phetchabun Branch |
|
3. Water source |
3.1
Small irrigation projects |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_05 |
Phetchabun Irrigation
Project |
|
3.2 Medium reservoir
information |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_06 |
Phetchabun Irrigation
Project |
|
|
3.3 |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_07 |
Phetchabun Irrigation
Project |
|
|
4. Artesian wells |
4.1 Groundwater well
information and groundwater use |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_08 |
Phetchabun Provincial
Office of Natural Resources and Environment |
|
4.2 Groundwater collection |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_09 |
|
|
|
5. Provincial Basic
Information |
Provincial Basic
Information |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_10 |
Phetchabun Province |
|
6. Rainfall |
Rainfall |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_13 |
Phetchabun Provincial
Meteorological Station |
|
7. Village plumbing |
Village Water Supply |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_14 |
Phetchabun Provincial
Local Government Promotion Office |
|
8. Suitability layer
(zoning) of economic cropping areas. |
Suitability layer (zoning)
of economic cropping areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_16 |
Phetchabun Land
Development Station |
|
9. Farm pond (miniature
pond) |
Farm pond (miniature pond) |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_17 |
Phetchabun Land
Development Station |
|
10. Growing saplings |
10.1 Annual rice
cultivation area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_19 |
Phetchabun Provincial
Agricultural Office |
|
10.2 Naprang rice
cultivation area Harvested land, yield and average yield per acre |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_20 |
Phetchabun Provincial
Agricultural Office |
|
|
10.3 Rice cultivation
area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_21 |
Phetchabun Provincial
Agricultural Office |
|
|
10.4 Cultivated area of
agronomy, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_22 |
Phetchabun Provincial
Agricultural Office |
|
|
10.5 Vegetable cultivated
area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_23 |
Phetchabun Provincial
Agricultural Office |
|
|
10.6 Cultivated areas for
fruit trees and perennials Harvested land, yield and average yield per acre |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_24 |
Phetchabun Provincial
Agricultural Office |
|
|
11.1 Drought-prone areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_11 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
|
11.2 Drought-affected areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_12 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
|
11.3 Repetitive drought areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_18 |
Phetchabun Land Development Station |
|
|
12. Drought Response Plan |
Drought Response Plan |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_02 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
13. Assistance to farmers who suffer from
disasters in case of emergencies (crop) |
Providing assistance to farmers who have
suffered from emergency disasters (crop) |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_04 |
Phetchabun Provincial Agricultural Office |
|
14. Drought resolution |
Visualization supports decision-making to resolve the drought problem of
Phetchabun Province. |
https://app.powerbi.com/view?r=eyJrIjoiZTY5ZmYxODctOWE0 New
00MTZjLTllMTItZjgxMzNjODQyNWY 3 IiwidCI6ImY 1 OTZlMjVhLTM5OWEtNDM 4
New1iYWFlLTMxMjZiODA4mmNhNCIsImMiOjEwfQ%3 D%3D |
Phetchabun Provincial
Statistics Office |
|
15. Drought Response Plan |
Drought Response Plan |
https://phetchabun.gdcatalog.go.th/dataset/cc45730e-e35a-40e6-a2dd-ec03530570c2/resource/cf786417-0580-41da-a072-a96f2711e71
e/download/02drought-response-plan.pdf |
Phetchabun Disaster
Prevention and Mitigation Office |
|
16. Weather conditions |
Summary of general weather conditions for the year |
https://www.tmd.go.th/climate/summaryyearly/2019 |
Department of Meteorology |
3.2. Data
Selection
This research
determines the finding of relationships between variables. The data is selected
by using the correlation statistics such as drought-prone areas,
drought-affected areas, repetitive drought areas, providing assistance to
farmers who have suffered from emergency disasters (crop), rainfall and summary
of general weather conditions for the year.
3.3. Analysis the
Drought Problem
1)
Data of drought
risk areas: the drought risk areas can
be divided into 3 levels, surveillance areas, moderate risk areas and high-risk
areas.
2)
Dryness: the drought
affects agricultural areas. The level of drought that occurs within 10 years divided
as follows: <=3 times in10 year-round, >6. 4-5 times in 10 year-round and
4-5 times in 10 year-round.
3)
Rainfall per
year: rain is the important factor in
the occurrence of drought in Phetchabun province.
4)
General weather
during the year-round: the highest and lowest average temperature in a year-round
affected to the agriculture and cattle during the winter season.
4. Results
and Analysis
From the section 3, the methodology is explained. The
researchers used 26 drought datasets from Phetchabun Province data catalog. The
data is selected to solve the drought problem. The drought factors are used to
analysis and visualization dashboard. The results can be help for decision
making to solve drought problem.
Figure 1 Drought area
Figure 1 is shown the drought area in the year 2020-2021. The drought area is divided by the districts which there
is the most damaged agricultural drought area. In year 2020, the drought area
is Chon Dan District, Wichian Buri District and Nam Nao District. In year 2021, the drought area is Si Thep District, Chon
Dan District and Bueng Sam Phan District. The Chon Dan District is the most
agricultural drought problem area.
Figure 2 Drought effect
Figure 2 is shown the drought effect
from the land using to agricultural. The total area of 1,257,756.3 square meters has the highest area of sugar cane cultivation
equal 368448.37 square meters, followed by rice field cultivation equal 262,942.43 square meters and corn cultivation equal 130,658.86
square
meters. The drought levels have
an effect in the land using. In the 10 year-round, the drought effect is often
frequency with agricultural. The <=3 times in the 10 year-round has effect
with land using in the rice field cultivation equal 127,093.59 square meters, followed by the sugar cane cultivation equal
121,352.64 square meters and corn
cultivation equal 61,11.26 square meters. The four-five times in the 10 year-round has effect with land using in
the sugar cane cultivation
equal 211,354.86 square meters, followed by the rice field cultivation
equal 110,959.47 square meters and corn cultivation equal 52,619.93 square meters. The six times in the 10 year-round has effect
with land using in the sugar cane cultivation equal 35,740.87 square meters, followed by the rice field cultivation
equal 24,889.37 square meters and corn cultivation equal 19,018.98 square meters.
Figure3 Rainfall
Table 3
Rainfall
|
month |
Rainfall (MM) |
||||||||
|
|
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
combine |
|
January |
0 |
0.7 |
42.2 |
57.3 |
27.5 |
0 |
0 |
0 |
127.7 |
|
February |
0 |
12.9 |
0 |
3.8 |
48.2 |
33.6 |
0 |
23.4 |
121.9 |
|
March |
4.3 |
41.7 |
0 |
40.9 |
67.4 |
56.2 |
43.1 |
2.9 |
252.2 |
|
April |
57.1 |
74 |
26.7 |
36.6 |
80.8 |
64.9 |
114 |
235.8 |
632.8 |
|
May |
121.8 |
60.2 |
138.7 |
352.2 |
160.3 |
134.3 |
124.3 |
68.8 |
1038.8 |
|
June |
127.6 |
45.7 |
141.7 |
168.1 |
111.9 |
75.8 |
205.9 |
102.2 |
851.3 |
|
July |
162.4 |
276 |
191.9 |
195 |
172.9 |
135.9 |
78.6 |
216.4 |
1266.7 |
|
August |
423.2 |
87.2 |
131.6 |
285.6 |
190.3 |
269.8 |
166 |
148 |
1278.5 |
|
September |
176.3 |
218.8 |
290.5 |
98.1 |
62.4 |
71.1 |
101.1 |
21.7 |
863.7 |
|
October |
84 |
123.1 |
49.1 |
117.8 |
94.8 |
37.6 |
105.1 |
|
527.5 |
|
November |
58.9 |
4.1 |
28.2 |
11.4 |
13.4 |
1.8 |
1.3 |
|
60.2 |
|
December |
0 |
28.7 |
0.8 |
9.4 |
2.9 |
0 |
0 |
|
41.8 |
|
average |
1,215.6 |
973.1 |
1,041.4 |
1,376.2 |
1,032.8 |
881 |
939.4 |
819.2 |
|
|
Average 8
years |
1,034.8 |
||||||||
Figure 3 illustrated the rainfall. An overview of the 8-year rainfall from year 2014-2021
has average rainfall of 1,034.8 mm. In year 2017, the highest average rainfall is
1,376.2 mm. The most of the rainfall is 352.2 mm. in May. In 2014, the average
rainfall is 1,215.6 mm. The most of the rainfall is 423.2 mm in August. In
2016, the average rainfall is 1,041.4 mm. The most of the rainfall is 290.5 mm
in September.
Figure 4 Temperature
Figure 4 presented the
highest and lowest average temperature in year 2020-2021. In 2020, the average temperature is 27.6 degrees
Celsius. The highest average temperature is 30.9. Degrees Celsius in May. The
average temperature is 30.6 degrees Celsius in April. The lowest average temperature is 23.30
degrees Celsius in December. In 2021, the average temperature is 26.9 degrees
Celsius. The highest average temperature is 29.8 degrees Celsius in May. The
average temperature is 28.7 degrees Celsius in June. The lowest average temperature is 22.7
degrees Celsius in December and January.
5. Conclusion
In this
paper, the study and analyze the influencing factors of drought in Phetchabun
province is proposed. The dataset of
drought problem is download from the government data catalog of Phetchabun
province. There are several factors used to analyze drought problem such as drought
area, drought effect, land using and temperature. The data is used to prepare
the visualization dashboard. The results show that drought is the significant
problem and affects to agriculture and economic system in Phetchabun province. The
provincial governor and committee use data-driven decision making to solve
drought problem. In the future work, the researcher will be use the
machine learning model for solve the drought problem.
6. References
Government Big Data Analysis and
Management Institute ( GBDi ) . (2021). [ Online ]. Book Public sector big data analytics
framework. [ Retrieved May
15, 2022 ]. From https://gbdi.depa.or.th/news/government-big-data-analytics-framework/
Provincial Development Strategy and
Information Group Phetchabun Provincial Office (2017). [ Online ]. Strategy for the development of the province. [ Retrieved May 15, 2022 ]. From https://www.phetchabun.go.th/main/
Office of the National Economic and Social
Development Council. (2021). [ Online ]. (Draft)
National Economic and Social Development Plan No. 13 ( B.E. 2566-2570). [ Retrieved May 15, 2022 ]. From https://www.nesdc.go.th/main.php?filename=develop_issue
statistical office Phetchabun Province . (
2022). [ Online]. Statistical
data . [Retrieved May 15 , 2022]. From http://phchabun.old.nso.go.th/nso/project/search/index.jsp?province_id=55
Government Accounting System . (2022).
[Online]. Accounting Information of Northern Region. [Retrieved May 15, 2022].
From https://gdhelppage.nso.go.th/p01_catalog16.html
Fung, K. F.,
Huang, Y. F., Koo, C. H., Mirzaei, M. (2020). Improved SVR machine learning
models for agricultural drought prediction at downstream of Langat River Basin,
Malaysia. Journal of Water and Climate Change, 11(4), 1383–1398. DOI
10.2166/wcc.2019.295.
Han, J., Singh,
V. P. (2020). Forecasting of droughts and tree mortality under global warming:
A review of causative mechanisms and modeling methods. Journal of Water and
Climate Change, 11(3), 600–632. DOI 10.2166/wcc.2020.239.
Khan, N.,
Sachindra, D.A., Shahid, S., Ahmed, K., Shiru, M.S., Nawaz, N. (2020).
Prediction of Droughts over Pakistan Using Machine Learning Algorithms.
Advances in Water Resources, 139(2020), 1-15. DOI
10.1016/j.advwatres.2020.103562.
Sundararajan, K.,
Garg, L., Srinivasan K., Bashir A. K., Kaliappan, J., Ganapathy, G. P.,
Selvaraj, S. K. and Meena, T. (2021). A Contemporary Review on Drought Modeling
Using Machine Learning Approaches, Computer Modeling in Engineering &
Sciences, 128(2), 447-487. DOI 10.32604/cmes.2021.015528.
Mishra, D.,
Goswami, S., Matin, S. and Sarup, J. (2021). Analyzing the extent of drought in
the Rajasthan state of India using vegetation condition index and standardized
precipitation index, Modeling Earth Systems and Environment, 8:601–610. DOI
10.1007/s40808-021-01102-x.
Mokhtari, R.,
Akhoondzadeh, M. (2021). Data fusion and machine learning algorithms for
drought forecasting using satellite data. Journal of the Earth and Space
Physics, 46(4), 231–246. DOI 10.22059/jesphys.2020.299445.1007199.
Mohammed, S., Elbeltagi, A., Bashir, B., Alsafadi,
K., Alsilibe, F., Alsalman, A., Zeraatpisheh, M., Sz´eles, A. and Hars´anyi, E. (2022). A comparative analysis
of data mining techniques for agricultural and hydrological drought prediction
in the eastern Mediterranean, Computers and Electronics in Agriculture, 197
(2022), 1-19. DOI 10.1016/j.compag.2022.106925.
Dikshit, A., Pradhan B. and Santosh, M. (2022).
Artificial neural networks in drought prediction in the 21st century –A scientometric analysis, Applied Soft
Computing 114 (2022), 1-17. DOI 10.1016/j.asoc.2021.108080.
1. Introduction
Nowadays, the government sectors and private
sectors are aware of the importance of analyzing and big data utilizing for the
decision-making and operations. The Office of the Civil Service Commission in collaboration with the Ministry of Digital for the
Economy and Society, the human resource development mechanism for the big data utilizing
has been proposed. The target group of this development consists of 3 groups as
follows: 1) The creator and system developer. 2) Analyst group, process and
display results. 3) Data user group, workgroups. The implement of government's
big data project can be divided into 3 tasks: 1. Working on creating and
maintaining big data information systems. 2. Data analysis and 3. Bringing the information
to use for the decision making (Government Big Data Analysis Framework, 2020)
The analyzing
and displaying of big data, in the paper proposed case study of drought problem
and effect in Phetchabun Province. The provincial governor of Phenchabun
province is importance to solve the drought problem and forward the policy of
solving the drought problem at the meeting of the data governance commit of
Phetchabun province. At the meeting of the Phetchabun Provincial Statistics
Committee No. 1/2021 on March 17, 2021, it was resolved to approve the
preparation of a dataset which related to the key issues in the area (Pain
Point). Phetchabun Province Drought Solution is at risk of drought since most
of the people of the province are mainly engaged in agriculture which still
relies mainly on natural water. Drought is a problem caused by natural
fluctuations coupled with human action affecting the shortage of water for
agriculture. (Requirements for Dataset Analysis for Key Issues, 2022)
In the Phetchabun
Province Annual Government Action Plan, Year Budget 2022, Volume 2, Project No.
25 Activities: Promote and link marketing of safe/organic agricultural
products, processed agriculture and related products. There are the important
agricultural products: such as mangoes, tamarinds, ginger, corn, sugarcane,
vegetables, medicinal plants, etc. And there are the agricultural products that
have been registered as commodities, geographical indication (Geographical
Indication: GI). Moreover, Phetchabun sweet tamarind from Khao Farm Leum Puea,
Phetchabun raising the level of agricultural products to meet the standards of
organic / safe agriculture products such as vegetables, fruits, herbs that are
not food, rice and cereal for household consumption and commercial development.
There are group of farmers in Phetchabun Province who have established
agricultural production plots, namely, 78 large plots, the Center for
Agricultural Product Production Efficiency (CAD) and a network of 219 centers,
1,479 community enterprises, 86 Smart Farmer prototypes and 46 Young Smart
Farmer prototypes.
It is
absolutely necessary to solve or prevent drought problems that occur or may
occur along with finding suitable measures and technologies to bring more land
to use. Including the restoration of forest areas. Especially the watershed
forest area. It increases the potential of the area to accumulate water in the
soil and groundwater planting perennials to add moisture to the dry land area.
Therefore, the researcher has taken the dataset from the government data
accounting to the system in Case Study of Phetchabun Province, the problem of
drought analyzed in order to use the data obtained to study the factors causing
the drought. Prepared in the form of diagrams, graphs and charts (Data
Visualization) and Prescriptive analytics to support the decision-making in
solving drought problems of Phetchabun Province.
2. Related Works
In the last
decades, climate change is regarded as one of the biggest challenges to the
earth because it’s causes and aggravates serious natural hazards including rain
storm-floods, forest fire, tsunami, droughts and many others. The drought
problem has been addressed by many authors because drought has a devastating
effect on the ecology as a potential hydro-meteorological disaster. Due to
extensive impacts of drought in past decades at regional and global scales
leads to improved capability to cope with drought. Thus, drought prediction
plays a key role in drought early warning to mitigate its impacts. At present,
there are a lot of researches on drought forecasting in many countries. In 2020, Han and Singh reviewed
forecasting methods for drought and tree mortality under global warming. This research examines
causative mechanisms for drought and tree mortality, and synthesizes
stochastic, statistical, dynamical, and hybrid statistical-dynamical drought
forecasting models as well as theoretical, empirical, and mechanistic tree
mortality forecasting models. The results from this research demonstrate that
some of the statistical drought forecasting models, which have nonlinear and
nonstationary natures, can be merged with dynamical models to compensate for
their lack of stochastic structure in order to improve forecasting skills.
Afterward, Fung, et al. proposed the improved SVR machine learning models for
predicting the standardized precipitation evapotranspiration indices (SPEI)
with a lead time of one month to minimize potential drought impact on oil palm
plantations at the downstream of Langat River Basin, Malaysia, which has a
tropical climate pattern. However, the potential of developing drought
prediction models over Pakistan using three state-of-the-art Machine Learning
(ML) techniques; Support Vector Machine (SVM), Artificial Neural Network (ANN)
and k-Nearest Neighbour (KNN) was investigated by Khan et al. (2020) which
based on the Standardized Precipitation and Evapotranspiration Index (SPEI). In
2021, Sundararajan, et al. proposed a contemporary review on drought modeling
Using Machine Learning Approaches. They found that the data-driven modelling
for forecasting the metrological time series prediction is becoming more
powerful and flexible with computational intelligence techniques which include
singular vector machines (SVM), support vector regression, random forest,
decision tree, logistic regression, Naive Bayes, linear
regression, gradient boosting tree, k-nearest neighbours (KNN), the adaptive neuro-fuzzy inference system, the feed-forward neural networks,
Markovian chain, Bayesian network, hidden Markov models, and
autoregressive moving averages, evolutionary algorithms, deep learning and many more. Furthermore, several researchers have been established more than 100 drought indices.
Some
applications of satellite data are presented in Mishra, et al. (2021) and
Mokhtari and Akhoondzadeh (2021).
Mishra, et al. (2021) analyzed the extent of drought in the Rajasthan
state of India using vegetation condition index and standardized precipitation
index. This study reconfirms that the use of RS technique for drought risk
assessment is reliable based on the results obtained in this study. Mokhtari
and Akhoondzadeh (2021) described data fusion and machine learning algorithms
for Drought forecasting using satellite data. The modeling of the NDVI index
monthly was performed by using TRMM rainfall data, SMOS satellite soil
moisture, MODIS land surface temperature, snow cover, evapotranspiration with
machine learning algorithms such as SVR algorithm, ANN algorithm, DT algorithm and RF
algorithm. The ANN algorithm has provided higher accuracy than the other three
algorithms.
In recent
years, data mining has been addressed by several successful applications for
drought prediction. For example, Mohammed, et al. (2022) applies data mining
for agricultural and hydrological drought prediction in the eastern
Mediterranean which has the main goals is to capture agricultural and
hydrological drought trends by using the Standardized Precipitation Index (SPI)
and to assess the applicability of four ML algorithms (bagging (BG), random
subspace (RSS), random tree (RT), and random forest (RF)) in predicting drought
events based on SPI-3 and SPI-12. The output could be helping decision-makers
with drought mitigation plans by using the new four machine learning
algorithms. Furthermore, several researchers have studied an artificial neural
network in drought prediction; for example, Dikshit, et al. (2022) provided a
comprehensive review of the various neural networks that have been
traditionally used to forecast droughts in various parts of the world. They
examine the most popular and often used neural network-based models and how
these have improved their understanding of drought forecasting.
Finally, the
machine learning model, drought index and country are used in drought
forecasting as shown in Table I.
Table 1
The machine learning model, drought index and country are used in drought
forecasting.
|
Model Used |
Drought Index |
Country |
|
ANN |
SPI, NADI,
ARID, NDVI, VCI, NDWI, WSVI, NDDI, SWSI |
India,
Australia, United States, Ethiopia, Iran, Kenya |
|
ANFIS, Fuzzy
Logic |
PMDI, SPI |
United
States, Iran, Turkey |
|
SVM |
SPI, SPEI |
Australia,
Pakistan, India |
|
RF |
SPI, SPEI |
Australia,
United States, China |
|
Hybrid Model |
PMDI, SPI,
EDI |
Australia,
United States, Iran, |
|
Deep Learning
Model |
SPI, SPEI |
Australia,
India |
|
ANFIS |
SPI |
Turkey |
|
ANFIS, FFNN |
SPI |
Turkey, Iran |
|
NN |
Palmer |
Iceland |
|
RMSNN, DMSNN,
ARIMA |
Nonlinear
Aggregated |
Australia |
|
ANN, SVR, WN |
SPI |
Ethiopia |
|
ANN, ANFI,
WA-ANN |
SPI |
Iran |
|
MLPANN,
ANFIS, SVM |
SPI |
Iran |
|
MLPNN |
SPEI |
Pakistan |
|
IIS-W-ANN |
SWL |
Australia |
|
DNN |
SPI |
United
Kingdom |
|
DLNM, ANN,
XGB |
ONI, SOI,
PDO, NAO, AMO, IPO |
China |
|
SVR |
SPEI |
China |
|
WFL |
PDSI |
USA |
|
WANN, WFL |
PMDI |
Turkey |
|
BN |
ESP_R, SRI,
SPI, SPEI, PHDI |
Korea, Peninsula |
|
RF |
SPI, SMI,
SPEI |
China, Korea,
Australia |
|
HMM |
SPI |
Korea,
Ethiopia |
|
Semi-Markov |
SDI |
Georgia |
3. Methodology
In this section, the methodology for analysis the
influencing factors of drought problem in Phetchabun Province is described as following.
3.1. Data
Collection and Preparation
The dataset
is download from the government data catalog platform,
which is available at the website: https://gdcatalog.go.th/ or https://phetchabun.gdcatalog.go.th/.
There are 26 datasets in Phetchabun catalog. The list of datasets of Phetchabun
Province as shown in Table 1 and the datasets are divided into 5 group as
follows:
1) Water
demand group (Agricultural sector, Household sector, Industrial sector) Scope
of issue Farmers register, farmer households, target groups register in Khok
Nong Na plot.
2) Water
allocation management (Calculate demand for irrigation water storage) scope of
issues water supply, water sources, artesian wells, provincial basic
information, rainfall, village water supply, zoning of economic crops, farm ponds
(mini ponds), cultivated area, irrigation area.
3) Drought
impacts (consumption, agriculture, environment) Scope of issue Farmers,
households, agricultural products deteriorated soil, dust, inclement weather.
4) Spatial
data (area affected by drought) natural water source space utilization scope of
issues Drought-prone areas, drought-affected areas, recurring drought areas,
dams, reservoirs, artesian wells.
5) Environmental
factors Scope of issue Rainfall amount Characteristics of the area Groundwater
sources, sea level, soil conditions.
Table 2
List of datasets
|
Scope of issues |
Dataset/Data Resource List |
URL |
note |
|
1. Farmer's register,
farmer household |
1.1 Farmer registration |
https://phetchabun.gdcatalog.go.th/dataset/dataset_ |
Phetchabun Provincial
Agricultural Office |
|
1.2 List of target groups
for Khok Nong Na plot |
https://phetchabun.gdcatalog.go.th/dataset/dataset_ |
Phetchabun
Provincial Community
Development Office |
|
|
2. Water supply
consumption |
2.1 Water consumption data |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_01 |
Provincial Water Supply
Authority Phetchabun Branch |
|
3. Water source |
3.1
Small irrigation projects |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_05 |
Phetchabun Irrigation
Project |
|
3.2 Medium reservoir
information |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_06 |
Phetchabun Irrigation
Project |
|
|
3.3 |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_07 |
Phetchabun Irrigation
Project |
|
|
4. Artesian wells |
4.1 Groundwater well
information and groundwater use |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_08 |
Phetchabun Provincial
Office of Natural Resources and Environment |
|
4.2 Groundwater collection |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_09 |
|
|
|
5. Provincial Basic
Information |
Provincial Basic
Information |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_10 |
Phetchabun Province |
|
6. Rainfall |
Rainfall |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_13 |
Phetchabun Provincial
Meteorological Station |
|
7. Village plumbing |
Village Water Supply |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_14 |
Phetchabun Provincial
Local Government Promotion Office |
|
8. Suitability layer
(zoning) of economic cropping areas. |
Suitability layer (zoning)
of economic cropping areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_16 |
Phetchabun Land
Development Station |
|
9. Farm pond (miniature
pond) |
Farm pond (miniature pond) |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_17 |
Phetchabun Land
Development Station |
|
10. Growing saplings |
10.1 Annual rice
cultivation area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_19 |
Phetchabun Provincial
Agricultural Office |
|
10.2 Naprang rice
cultivation area Harvested land, yield and average yield per acre |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_20 |
Phetchabun Provincial
Agricultural Office |
|
|
10.3 Rice cultivation
area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_21 |
Phetchabun Provincial
Agricultural Office |
|
|
10.4 Cultivated area of
agronomy, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_22 |
Phetchabun Provincial
Agricultural Office |
|
|
10.5 Vegetable cultivated
area, harvested area, yield and average yield per rai |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_23 |
Phetchabun Provincial
Agricultural Office |
|
|
10.6 Cultivated areas for
fruit trees and perennials Harvested land, yield and average yield per acre |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_24 |
Phetchabun Provincial
Agricultural Office |
|
|
11.1 Drought-prone areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_11 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
|
11.2 Drought-affected areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_12 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
|
11.3 Repetitive drought areas |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_18 |
Phetchabun Land Development Station |
|
|
12. Drought Response Plan |
Drought Response Plan |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_02 |
Phetchabun Disaster Prevention and Mitigation
Office |
|
13. Assistance to farmers who suffer from
disasters in case of emergencies (crop) |
Providing assistance to farmers who have
suffered from emergency disasters (crop) |
https://phetchabun.gdcatalog.go.th/dataset/dataset_10_04 |
Phetchabun Provincial Agricultural Office |
|
14. Drought resolution |
Visualization supports decision-making to resolve the drought problem of
Phetchabun Province. |
https://app.powerbi.com/view?r=eyJrIjoiZTY5ZmYxODctOWE0 New
00MTZjLTllMTItZjgxMzNjODQyNWY 3 IiwidCI6ImY 1 OTZlMjVhLTM5OWEtNDM 4
New1iYWFlLTMxMjZiODA4mmNhNCIsImMiOjEwfQ%3 D%3D |
Phetchabun Provincial
Statistics Office |
|
15. Drought Response Plan |
Drought Response Plan |
https://phetchabun.gdcatalog.go.th/dataset/cc45730e-e35a-40e6-a2dd-ec03530570c2/resource/cf786417-0580-41da-a072-a96f2711e71
e/download/02drought-response-plan.pdf |
Phetchabun Disaster
Prevention and Mitigation Office |
|
16. Weather conditions |
Summary of general weather conditions for the year |
https://www.tmd.go.th/climate/summaryyearly/2019 |
Department of Meteorology |
3.2. Data
Selection
This research
determines the finding of relationships between variables. The data is selected
by using the correlation statistics such as drought-prone areas,
drought-affected areas, repetitive drought areas, providing assistance to
farmers who have suffered from emergency disasters (crop), rainfall and summary
of general weather conditions for the year.
3.3. Analysis the
Drought Problem
1)
Data of drought
risk areas: the drought risk areas can
be divided into 3 levels, surveillance areas, moderate risk areas and high-risk
areas.
2)
Dryness: the drought
affects agricultural areas. The level of drought that occurs within 10 years divided
as follows: <=3 times in10 year-round, >6. 4-5 times in 10 year-round and
4-5 times in 10 year-round.
3)
Rainfall per
year: rain is the important factor in
the occurrence of drought in Phetchabun province.
4)
General weather
during the year-round: the highest and lowest average temperature in a year-round
affected to the agriculture and cattle during the winter season.
4. Results
and Analysis
From the section 3, the methodology is explained. The
researchers used 26 drought datasets from Phetchabun Province data catalog. The
data is selected to solve the drought problem. The drought factors are used to
analysis and visualization dashboard. The results can be help for decision
making to solve drought problem.
Figure 1 Drought area
Figure 1 is shown the drought area in the year 2020-2021. The drought area is divided by the districts which there
is the most damaged agricultural drought area. In year 2020, the drought area
is Chon Dan District, Wichian Buri District and Nam Nao District. In year 2021, the drought area is Si Thep District, Chon
Dan District and Bueng Sam Phan District. The Chon Dan District is the most
agricultural drought problem area.
Figure 2 Drought effect
Figure 2 is shown the drought effect
from the land using to agricultural. The total area of 1,257,756.3 square meters has the highest area of sugar cane cultivation
equal 368448.37 square meters, followed by rice field cultivation equal 262,942.43 square meters and corn cultivation equal 130,658.86
square
meters. The drought levels have
an effect in the land using. In the 10 year-round, the drought effect is often
frequency with agricultural. The <=3 times in the 10 year-round has effect
with land using in the rice field cultivation equal 127,093.59 square meters, followed by the sugar cane cultivation equal
121,352.64 square meters and corn
cultivation equal 61,11.26 square meters. The four-five times in the 10 year-round has effect with land using in
the sugar cane cultivation
equal 211,354.86 square meters, followed by the rice field cultivation
equal 110,959.47 square meters and corn cultivation equal 52,619.93 square meters. The six times in the 10 year-round has effect
with land using in the sugar cane cultivation equal 35,740.87 square meters, followed by the rice field cultivation
equal 24,889.37 square meters and corn cultivation equal 19,018.98 square meters.
Figure3 Rainfall
Table 3
Rainfall
|
month |
Rainfall (MM) |
||||||||
|
|
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
combine |
|
January |
0 |
0.7 |
42.2 |
57.3 |
27.5 |
0 |
0 |
0 |
127.7 |
|
February |
0 |
12.9 |
0 |
3.8 |
48.2 |
33.6 |
0 |
23.4 |
121.9 |
|
March |
4.3 |
41.7 |
0 |
40.9 |
67.4 |
56.2 |
43.1 |
2.9 |
252.2 |
|
April |
57.1 |
74 |
26.7 |
36.6 |
80.8 |
64.9 |
114 |
235.8 |
632.8 |
|
May |
121.8 |
60.2 |
138.7 |
352.2 |
160.3 |
134.3 |
124.3 |
68.8 |
1038.8 |
|
June |
127.6 |
45.7 |
141.7 |
168.1 |
111.9 |
75.8 |
205.9 |
102.2 |
851.3 |
|
July |
162.4 |
276 |
191.9 |
195 |
172.9 |
135.9 |
78.6 |
216.4 |
1266.7 |
|
August |
423.2 |
87.2 |
131.6 |
285.6 |
190.3 |
269.8 |
166 |
148 |
1278.5 |
|
September |
176.3 |
218.8 |
290.5 |
98.1 |
62.4 |
71.1 |
101.1 |
21.7 |
863.7 |
|
October |
84 |
123.1 |
49.1 |
117.8 |
94.8 |
37.6 |
105.1 |
|
527.5 |
|
November |
58.9 |
4.1 |
28.2 |
11.4 |
13.4 |
1.8 |
1.3 |
|
60.2 |
|
December |
0 |
28.7 |
0.8 |
9.4 |
2.9 |
0 |
0 |
|
41.8 |
|
average |
1,215.6 |
973.1 |
1,041.4 |
1,376.2 |
1,032.8 |
881 |
939.4 |
819.2 |
|
|
Average 8
years |
1,034.8 |
||||||||
Figure 3 illustrated the rainfall. An overview of the 8-year rainfall from year 2014-2021
has average rainfall of 1,034.8 mm. In year 2017, the highest average rainfall is
1,376.2 mm. The most of the rainfall is 352.2 mm. in May. In 2014, the average
rainfall is 1,215.6 mm. The most of the rainfall is 423.2 mm in August. In
2016, the average rainfall is 1,041.4 mm. The most of the rainfall is 290.5 mm
in September.
Figure 4 Temperature
Figure 4 presented the
highest and lowest average temperature in year 2020-2021. In 2020, the average temperature is 27.6 degrees
Celsius. The highest average temperature is 30.9. Degrees Celsius in May. The
average temperature is 30.6 degrees Celsius in April. The lowest average temperature is 23.30
degrees Celsius in December. In 2021, the average temperature is 26.9 degrees
Celsius. The highest average temperature is 29.8 degrees Celsius in May. The
average temperature is 28.7 degrees Celsius in June. The lowest average temperature is 22.7
degrees Celsius in December and January.
5. Conclusion
In this
paper, the study and analyze the influencing factors of drought in Phetchabun
province is proposed. The dataset of
drought problem is download from the government data catalog of Phetchabun
province. There are several factors used to analyze drought problem such as drought
area, drought effect, land using and temperature. The data is used to prepare
the visualization dashboard. The results show that drought is the significant
problem and affects to agriculture and economic system in Phetchabun province. The
provincial governor and committee use data-driven decision making to solve
drought problem. In the future work, the researcher will be use the
machine learning model for solve the drought problem.
6. References
Government Big Data Analysis and
Management Institute ( GBDi ) . (2021). [ Online ]. Book Public sector big data analytics
framework. [ Retrieved May
15, 2022 ]. From https://gbdi.depa.or.th/news/government-big-data-analytics-framework/
Provincial Development Strategy and
Information Group Phetchabun Provincial Office (2017). [ Online ]. Strategy for the development of the province. [ Retrieved May 15, 2022 ]. From https://www.phetchabun.go.th/main/
Office of the National Economic and Social
Development Council. (2021). [ Online ]. (Draft)
National Economic and Social Development Plan No. 13 ( B.E. 2566-2570). [ Retrieved May 15, 2022 ]. From https://www.nesdc.go.th/main.php?filename=develop_issue
statistical office Phetchabun Province . (
2022). [ Online]. Statistical
data . [Retrieved May 15 , 2022]. From http://phchabun.old.nso.go.th/nso/project/search/index.jsp?province_id=55
Government Accounting System . (2022).
[Online]. Accounting Information of Northern Region. [Retrieved May 15, 2022].
From https://gdhelppage.nso.go.th/p01_catalog16.html
Fung, K. F.,
Huang, Y. F., Koo, C. H., Mirzaei, M. (2020). Improved SVR machine learning
models for agricultural drought prediction at downstream of Langat River Basin,
Malaysia. Journal of Water and Climate Change, 11(4), 1383–1398. DOI
10.2166/wcc.2019.295.
Han, J., Singh,
V. P. (2020). Forecasting of droughts and tree mortality under global warming:
A review of causative mechanisms and modeling methods. Journal of Water and
Climate Change, 11(3), 600–632. DOI 10.2166/wcc.2020.239.
Khan, N.,
Sachindra, D.A., Shahid, S., Ahmed, K., Shiru, M.S., Nawaz, N. (2020).
Prediction of Droughts over Pakistan Using Machine Learning Algorithms.
Advances in Water Resources, 139(2020), 1-15. DOI
10.1016/j.advwatres.2020.103562.
Sundararajan, K.,
Garg, L., Srinivasan K., Bashir A. K., Kaliappan, J., Ganapathy, G. P.,
Selvaraj, S. K. and Meena, T. (2021). A Contemporary Review on Drought Modeling
Using Machine Learning Approaches, Computer Modeling in Engineering &
Sciences, 128(2), 447-487. DOI 10.32604/cmes.2021.015528.
Mishra, D.,
Goswami, S., Matin, S. and Sarup, J. (2021). Analyzing the extent of drought in
the Rajasthan state of India using vegetation condition index and standardized
precipitation index, Modeling Earth Systems and Environment, 8:601–610. DOI
10.1007/s40808-021-01102-x.
Mokhtari, R.,
Akhoondzadeh, M. (2021). Data fusion and machine learning algorithms for
drought forecasting using satellite data. Journal of the Earth and Space
Physics, 46(4), 231–246. DOI 10.22059/jesphys.2020.299445.1007199.
Mohammed, S., Elbeltagi, A., Bashir, B., Alsafadi,
K., Alsilibe, F., Alsalman, A., Zeraatpisheh, M., Sz´eles, A. and Hars´anyi, E. (2022). A comparative analysis
of data mining techniques for agricultural and hydrological drought prediction
in the eastern Mediterranean, Computers and Electronics in Agriculture, 197
(2022), 1-19. DOI 10.1016/j.compag.2022.106925.
Dikshit, A., Pradhan B. and Santosh, M. (2022).
Artificial neural networks in drought prediction in the 21st century –A scientometric analysis, Applied Soft
Computing 114 (2022), 1-17. DOI 10.1016/j.asoc.2021.108080.
ความคิดเห็น
แสดงความคิดเห็น