Detection of Drought Behavioral Patterns and Its Prediction Using Web-Based Expert Systems

Nagahi, M.; Behzadi, S.

doi:10.22061/jrsgr.2024.10772.1063

Document Type : Original Research Paper

Authors

Department of Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran

https://doi.org/10.22061/jrsgr.2024.10772.1063

Abstract

Background and Objectives: Drought is a persistent and critical challenge that affects many countries around the world, including Iran. This natural phenomenon can have severe economic, social, and environmental consequences, making the study and prediction of drought an important focus for researchers and experts. The primary objective of this paper is to predict drought using an expert system and to find an appropriate behavioral model for this phenomenon across all provinces of Iran. Drought is a complex and multifaceted issue that can have far-reaching impacts. In Iran, where water scarcity is a longstanding concern, drought can exacerbate existing challenges and lead to significant disruptions in various sectors, such as agriculture, water supply, and energy production. Accurate and timely prediction of drought can help policymakers and stakeholders implement effective mitigation and adaptation strategies, thereby minimizing the adverse effects of this natural disaster.
Methods: This study utilized data related to drought in all provinces of Iran from 2009 to 2021. These data include various drought indices, such as precipitation, temperature, humidity, and climate change indicators. Using these data, the researchers developed monthly behavioral models of drought for each province, employing an expert system and artificial intelligence techniques. The researchers first examined the drought patterns and trends in each province to identify suitable behavioral models. This process involved analyzing the historical data and identifying the key factors that influence drought patterns in the different regions of Iran. By leveraging the expertise of domain experts and the capabilities of advanced analytical tools, the researchers were able to construct comprehensive behavioral models that capture the complexity of drought dynamics. The development of these monthly behavioral models for each province was a critical step in the research process. By modeling the drought patterns at a granular, provincial level, the researchers were able to account for the unique geographic, climatic, and socioeconomic characteristics of each region. This approach enabled the creation of tailored predictions that can be more effectively utilized by decision-makers at the local and provincial levels.
Findings: The results of this study demonstrated that the use of drought data from all provinces of Iran and the development of monthly behavioral models can indeed facilitate the prediction of drought in each province on a monthly basis. The researchers were able to produce twelve behavioral models for each province, representing the probability of drought occurrence in different months. These models can serve as powerful tools in managing and planning to combat drought at both the provincial and national levels. By providing accurate and timely predictions of drought, policymakers and stakeholders can make more informed decisions regarding water resource management, agricultural planning, and disaster response strategies. The findings also highlighted the importance of an integrated, expert-driven approach to drought prediction. By leveraging the expertise of domain experts and the capabilities of advanced analytical tools, the researchers were able to develop comprehensive and reliable behavioral models that capture the nuances of drought dynamics in Iran.Conclusion: The findings of this study have significant implications for drought management and decision-making in Iran. By using an expert system and behavioral modeling of drought across all provinces, the researchers were able to achieve more accurate and timely predictions of this phenomenon. The linear model was selected as the best model, and an online web-based map was created to display the probability of drought for each province on a monthly basis. This web-based tool can serve as a valuable resource for policymakers, stakeholders, and the general public, facilitating informed decision-making and drought management at various levels. The availability of this information can lead to the reduction of the impacts and consequences of drought, enabling more effective planning and mitigation strategies to be implemented. The comprehensive and systematic approach used in this study can be replicated in other regions or countries facing similar drought-related challenges. By leveraging the power of expert systems, artificial intelligence, and behavioral modeling, researchers and policymakers can work together to develop robust drought prediction and management frameworks that enhance resilience and sustainability in the face of this critical natural phenomenon.

Keywords

Main Subjects

Geo-spatial Information System

COPYRIGHTS
© 2024 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/)

References

[1] Maybank J, Bonsai B, Jones K, Lawford R, O'brien E, Ripley E, et al. Drought as a natural disaster. Atmosphere-Ocean. 1995;33(2):195-222.

[2] Mohammadi J, Vafaeinezhad A, Behzadi S, Aghamohammadi H, Hemmasi A. Drought prediction and modeling by hybrid wavelet method and neural network algorithms. Journal of RS and GIS for Natural Resources. 2022;13(4):13-6.

[3] Karimi P, Safaval PA, Behzadi S, Azizi Z, Zarkash MMK, Kalashami HK. Flood Risk Zoning Using Geographical Information System Case Study: Khorramabad Flood in April 2019. Acta hydrotechnica. 2022;35(63):89-100.

[4] Jalilzadeh A, Behzadi S, editors. Flood Mapping and Estimation of Flood Water-Level Using Fuzzy Method and Remote Sensing Imagery (Case Study: Golestan Province, Iran). Forum Geografic; 2020: University of Craiova, Department of Geography.

[5] Behzadi S, Mousavi Z, Norouzi E. Mapping Historical Water-Supply Qanat Based On Fuzzy Method. An Application to the Isfahan Qanat (Isfahan, Iran). International Journal of Numerical Methods in Civil Engineering. 2019;3(4):24-32.

[6] SHIRAVAND H, KHALEDI S, BEHZADI S, Shokri SHA. Monitoring and assessing the changes in the coverage and decline of oak forests in Lorestan Province using Satellite Images and BFAST Model. 2020.

[7] Norouzi E, Behzadi S. Evaluating machine learning methods and satellite images to estimate combined climatic indices. International Journal of Numerical Methods in Civil Engineering. 2019;4(1):30-8.

[8] Norouzi E, Behzadi S. The Feasibility of Machine-learning Methods to Extract the Surface Evaporation Quantity using Satellite Imagery. Journal of Electrical and Computer Engineering Innovations (JECEI). 2021;9(2):229-38.

[9] Mousavi Z, Behzadi S. Geo-Portal Implementation with a Combined Approach of AHP and SWOT. International Journal of Natural Sciences Research. 2019;7(1):23-31.

[10] Mousavi Z, Behzadi S. Introducing an Appropriate Geoportal Structure for Managing Wildlife Location Data. International Journal of Natural Sciences Research. 2019;7(1):32-48.

[11] Hosseini-Moghari S.M., Araghinejad Sh. Application of Statistical, Fuzzy and Perceptron Neural Networks in Drought Forecasting (Case Study: Gonbad-e Kavous Station). Journal of Water and Soil. 2016;30(1):247-259.

[12] Hassanzadeh Y., Abdi Kordani A., Fakheri Fard A.. Drought Forecasting Using Genetic Algorithm and Conjoined Model of Neural Network-Wavelet. Journal of Water and Wastewater. 2012;23(3):48-59.

[13] Awan JA, Bae DH. Drought prediction over the East Asian monsoon region using the adaptive neuro‐fuzzy inference system and the global sea surface temperature anomalies. IJCli. 2016;36(15):4767-77.

[14] Shirmohammadi B, Moradi H, Moosavi V, Semiromi MT, Zeinali A. Forecasting of meteorological drought using Wavelet-ANFIS hybrid model for different time steps (case study: southeastern part of east Azerbaijan province, Iran). Natural hazards. 2013;69(1):389-402.

[15] Behzadi S, Jalilzadeh A. Introducing a Novel Digital Elevation Model Using Artificial Neural Network Algorithm. Civil Engineering Dimension. 2020;22(2):47-51.

[16] Mokhtarzad M, Eskandari F, Jamshidi Vanjani N, Arabasadi A. Drought forecasting by ANN, ANFIS, and SVM and comparison of the models. Environmental earth sciences. 2017;76:1-10.

[17] Arandian N, Behzadi S. Providing a Web-Based Platform Based on Predicted Weights from Existing Conditions. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020;42:1169-72.

[18] Ghasempoor Z, Behzadi S. Provide an Automated Web-based Platform for Collecting Traffic Data. Journal of Geomatics Science and Technology. 2022;12(1):171-86.

[19] Barzegari S, Agahamohammadi H, Behzadi S. Development of a Strategy Using Spatial Analysis and Neural Network for Spatial Analysis of Water Levels at the Time of Drought. Journal of Geomatics Science and Technology. 2020;9(3):73-84.

[20] Mahjoobi M, Behzadi S. Solar desalination site selection on the Caspian Sea coast using AHP and fuzzy logic methods. Modeling Earth Systems and Environment. 2022:1-9.

[21] Poorazizi E, Alesheikh A, Behzadi S. Developing a mobile GIS for field geospatial data acquisition. J Appl Sci. 2008;8(18):3279-83.

[22] Ghasempoor Z, Behzadi S. Traffic Modeling and Prediction Using Basic Neural Network and Wavelet Neural Network Along with Traffic Optimization Using Genetic Algorithm, Particle Swarm, and Colonial Competition. Journal of Geomatics Science and Technology. 2021;10(3):147-63.

[23] Ghasempoor Z, Behzadi S. Predicting Traffic Data in GIS using Different Neural Network Methods. International Journal of Geography and Geology. 2022;11(2):62-71.

[24] Schober P, Boer C, Schwarte LA. Correlation coefficients: appropriate use and interpretation. Anesthesia & Analgesia. 2018;126(5):1763-8.