Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China
Drought is a natural disaster that occurs globally and can damage the environment, disrupt agricultural production and cause large economic losses. The accurate prediction of drought can effectively reduce the impacts of droughts. Deep learning methods have shown promise in drought prediction, with...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Atmosphere |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4433/15/2/155 |
_version_ | 1797298996404813824 |
---|---|
author | Zixuan Chen Guojie Wang Xikun Wei Yi Liu Zheng Duan Yifan Hu Huiyan Jiang |
author_facet | Zixuan Chen Guojie Wang Xikun Wei Yi Liu Zheng Duan Yifan Hu Huiyan Jiang |
author_sort | Zixuan Chen |
collection | DOAJ |
description | Drought is a natural disaster that occurs globally and can damage the environment, disrupt agricultural production and cause large economic losses. The accurate prediction of drought can effectively reduce the impacts of droughts. Deep learning methods have shown promise in drought prediction, with convolutional neural networks (CNNs) being particularly effective in handling spatial information. In this study, we employed a deep learning approach to predict drought in the Fenhe River (FHR) basin, taking into account the meteorological conditions of surrounding regions. We used the daily SAPEI (Standardized Antecedent Precipitation Evapotranspiration Index) as the drought evaluation index. Our results demonstrate the effectiveness of the CNN model in predicting drought events 1~10 days in advance. We evaluated the predictions made by the model; the average Nash–Sutcliffe efficiency (NSE) between the predicted and true values for the next 10 days was 0.71. While the prediction accuracy slightly decreased with longer prediction lengths, the model remained stable and effective in predicting heavy drought events that are typically difficult to predict. Additionally, key meteorological variables for drought predictions were identified, and we found that training the CNN model with these key variables led to higher prediction accuracy than training it with all variables. This study approves an effective deep learning approach for daily drought prediction, particularly when considering the meteorological conditions of surrounding regions. |
first_indexed | 2024-03-07T22:43:09Z |
format | Article |
id | doaj.art-f4db6c4551b342ef8380c649133a9343 |
institution | Directory Open Access Journal |
issn | 2073-4433 |
language | English |
last_indexed | 2024-03-07T22:43:09Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Atmosphere |
spelling | doaj.art-f4db6c4551b342ef8380c649133a93432024-02-23T15:07:01ZengMDPI AGAtmosphere2073-44332024-01-0115215510.3390/atmos15020155Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, ChinaZixuan Chen0Guojie Wang1Xikun Wei2Yi Liu3Zheng Duan4Yifan Hu5Huiyan Jiang6Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Civil and Environmental Engineering, University of New South Wales, Sydney 2052, AustraliaDepartment of Physical Geography and Ecosystem Science, Lund University, SE-22362 Lund, SwedenCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDrought is a natural disaster that occurs globally and can damage the environment, disrupt agricultural production and cause large economic losses. The accurate prediction of drought can effectively reduce the impacts of droughts. Deep learning methods have shown promise in drought prediction, with convolutional neural networks (CNNs) being particularly effective in handling spatial information. In this study, we employed a deep learning approach to predict drought in the Fenhe River (FHR) basin, taking into account the meteorological conditions of surrounding regions. We used the daily SAPEI (Standardized Antecedent Precipitation Evapotranspiration Index) as the drought evaluation index. Our results demonstrate the effectiveness of the CNN model in predicting drought events 1~10 days in advance. We evaluated the predictions made by the model; the average Nash–Sutcliffe efficiency (NSE) between the predicted and true values for the next 10 days was 0.71. While the prediction accuracy slightly decreased with longer prediction lengths, the model remained stable and effective in predicting heavy drought events that are typically difficult to predict. Additionally, key meteorological variables for drought predictions were identified, and we found that training the CNN model with these key variables led to higher prediction accuracy than training it with all variables. This study approves an effective deep learning approach for daily drought prediction, particularly when considering the meteorological conditions of surrounding regions.https://www.mdpi.com/2073-4433/15/2/155droughtpredictiondeep learningCNN |
spellingShingle | Zixuan Chen Guojie Wang Xikun Wei Yi Liu Zheng Duan Yifan Hu Huiyan Jiang Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China Atmosphere drought prediction deep learning CNN |
title | Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China |
title_full | Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China |
title_fullStr | Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China |
title_full_unstemmed | Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China |
title_short | Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China |
title_sort | basin scale daily drought prediction using convolutional neural networks in fenhe river basin china |
topic | drought prediction deep learning CNN |
url | https://www.mdpi.com/2073-4433/15/2/155 |
work_keys_str_mv | AT zixuanchen basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT guojiewang basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT xikunwei basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT yiliu basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT zhengduan basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT yifanhu basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina AT huiyanjiang basinscaledailydroughtpredictionusingconvolutionalneuralnetworksinfenheriverbasinchina |