|
Development of an LSTM-based Forecasting Modelrnfor Agricultural Water Availability in Recurrent Flood and Drought-Prone Areas: A Case Study of Maha SarakhamrnProvince, Thailand |
|---|---|
| รหัสดีโอไอ | |
| Creator | Nittaya Pasukphun |
| Title | Development of an LSTM-based Forecasting Modelrnfor Agricultural Water Availability in Recurrent Flood and Drought-Prone Areas: A Case Study of Maha SarakhamrnProvince, Thailand |
| Contributor | Angsuma Kanchak, Chompoo Nuasri, Potsirin Limpinan, Yanasinee Suma |
| Publisher | Thai Society of Higher Education Institutes on Environment |
| Publication Year | 2569 |
| Journal Title | EnvironmentAsia |
| Journal Vol. | 19 |
| Journal No. | 3 |
| Page no. | 98-109 |
| Keyword | Water management, Flooding area, Drought-Prone Areas, Long Short-TermMemory (LSTM) |
| URL Website | http://www.tshe.org/ea/index.html |
| Website title | EnvironmentAsia |
| ISSN | 1906-1714 |
| Abstract | This research addresses the challenges of recurring floods and droughts in MaharnSarakham Province, Thailand, exacerbated by climate change. The study develops anrnLSTM-based forecasting model by integrating community-based insights with deep learning.rnA Long Short-Term Memory (LSTM) neural network was trained on a time-series datasetrn(2006–2022) comprising water levels from two key stations (E-8A and E-91) and fourrnmeteorological parameters: rainfall, temperature, relative humidity, and number of rainy days.rnData preprocessing was involved moving average and linear interpolation to handle missingrnvalues, followed by Min-Max normalization. The developed LSTM model demonstrated highrnaccuracy (RMSE = 0.9146, MAPE = 0.53%, and R2 = 0.9596), significantly outperformingrnthe ARIMA baseline model. Future forecasts capture seasonal trends, predicting lower waterrnlevels during the dry season with a return to average levels at the onset of the rainy season. Thisrnmodel serves as a practical tool for regional water management and early warning systems,rnsupporting drought preparedness and agricultural water allocation. |
