Basin-Scale Daily Drought Prediction Using Convolutional Neural Networks in Fenhe River Basin, China

Abstract

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.

Investigating the Response of Vegetation to Flash Droughts by Using Cross-Spectral Analysis and an Evapotranspiration-Based Drought Index

“…There are promising directions for future work to further explore insights into the response of vegetation to flash drought. Given the complex relationship between vegetation conditions and flash drought, future research should focus on machine learning algorithms such as eXtreme Gradient Boosting (XGBoost) [90,91], Random Forest [92,93], SVM [94], and the Convolutional Neural Network (CNN) [95] that can effectively capture their relationships. Among these machine learning methods, the CNN algorithm performs better in feature extraction, pattern recognition, and multi-scale analysis, facilitating the exploration of the relationship between flash drought and vegetation [95].…”

“…Given the complex relationship between vegetation conditions and flash drought, future research should focus on machine learning algorithms such as eXtreme Gradient Boosting (XGBoost) [90,91], Random Forest [92,93], SVM [94], and the Convolutional Neural Network (CNN) [95] that can effectively capture their relationships. Among these machine learning methods, the CNN algorithm performs better in feature extraction, pattern recognition, and multi-scale analysis, facilitating the exploration of the relationship between flash drought and vegetation [95]. Future research should also further explore the relationship between vegetation and flash droughts from historical inventory data and ground station data based on the method proposed in this study, as well as to evaluate the use of other drought indicators (e.g., DISS-Drought Information Satellite System [18,19]), which will help us in better understanding the response of vegetation to drought and in supporting the policy designation of water resource management and agricultural planning to reduce the impact of drought on agricultural production.…”