<p>Meteorological drought, exacerbated by global climate change, is a recurrent and complex catastrophe that disrupts water resources, agriculture, and economies worldwide. Forecasting future drought conditions is therefore of utmost importance in facilitating effective intervention and adaptation strategies. Artificial intelligence and machine learning techniques have gained attention owing to their potential in forecasting drought severity. However, they are often criticized for their black-box nature and lack of explainability and interpretability. To address this issue, this study explores the potential of local and global explainable artificial intelligence (XAI) tools, including SHAP and LIME, to extract intrinsic characteristics from different drought indices, including Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) and climatic parameters (temperature, relative humidity, and wind speed). These techniques were applied to understand the driving forces behind drought events under different scenarios. SHAP was used to provide global model explanations, revealing how climatic parameters varied in importance across stations and scenarios, while LIME was employed to offer local explanations for specific predictions, highlighting the role of lag time and the significance of each parameter in individual forecasting scenarios. Using data from four meteorological stations in the Konya province of Türkiye, spanning 1965 to 2023, six ensemble-based machine learning models were employed to forecast SPI and SPEI values at 6-month and 12-month scales, resulting in a total of 768 scenarios. Widely used evaluation metrics, namely MSE, RMSE, MAE, MAPE and <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="477_2025_3007_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="26" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:{R}^{2},\)</EquationSource> </InlineEquation> were employed to compare model performances. The prediction accuracy ranged from 0.513 to 0.864 <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="477_2025_3007_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:{R}^{2}\)</EquationSource> </InlineEquation> values, and CatBoost emerged as the best-performing method in the scenario in which SPEI-12 (t), SPEI-12 (t-1), temperature (T), and wind speed (W) were used as inputs. The global explanation using the SHAP revealed that climatic parameters had varying degrees of impact across stations and scenarios, whereas the influence of lag time was significant in the predictive models. Alongside these considerations, LIME and SHAP methods were applied to investigate the status of the parameters at local and global levels. LIME and SHAP analyses also revealed that T and W parameters played less decisive roles at all stations than SPEI(t) and SPEI(t-1) parameters. The conclusion drawn from the current investigation may offer more explainability when working with machine learning algorithms in drought prediction studies, which could be critical for predicting future drought events.</p>

Explainable artificial intelligence to explore the intrinsic characteristics of climatic parameters governing meteorological drought forecasting: opening the black box

期刊论文
出版模式：

开放获取
发表日期：

2025年6月2日

查看全文

Ertugrul Ozupek,
Alihan Teke,
Nuri Celik,
Taskin Kavzoglu

摘要

Meteorological drought, exacerbated by global climate change, is a recurrent and complex catastrophe that disrupts water resources, agriculture, and economies worldwide. Forecasting future drought conditions is therefore of utmost importance in facilitating effective intervention and adaptation strategies. Artificial intelligence and machine learning techniques have gained attention owing to their potential in forecasting drought severity. However, they are often criticized for their black-box nature and lack of explainability and interpretability. To address this issue, this study explores the potential of local and global explainable artificial intelligence (XAI) tools, including SHAP and LIME, to extract intrinsic characteristics from different drought indices, including Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) and climatic parameters (temperature, relative humidity, and wind speed). These techniques were applied to understand the driving forces behind drought events under different scenarios. SHAP was used to provide global model explanations, revealing how climatic parameters varied in importance across stations and scenarios, while LIME was employed to offer local explanations for specific predictions, highlighting the role of lag time and the significance of each parameter in individual forecasting scenarios. Using data from four meteorological stations in the Konya province of Türkiye, spanning 1965 to 2023, six ensemble-based machine learning models were employed to forecast SPI and SPEI values at 6-month and 12-month scales, resulting in a total of 768 scenarios. Widely used evaluation metrics, namely MSE, RMSE, MAE, MAPE and \(\:{R}^{2},\) were employed to compare model performances. The prediction accuracy ranged from 0.513 to 0.864 \(\:{R}^{2}\) values, and CatBoost emerged as the best-performing method in the scenario in which SPEI-12 (t), SPEI-12 (t-1), temperature (T), and wind speed (W) were used as inputs. The global explanation using the SHAP revealed that climatic parameters had varying degrees of impact across stations and scenarios, whereas the influence of lag time was significant in the predictive models. Alongside these considerations, LIME and SHAP methods were applied to investigate the status of the parameters at local and global levels. LIME and SHAP analyses also revealed that T and W parameters played less decisive roles at all stations than SPEI(t) and SPEI(t-1) parameters. The conclusion drawn from the current investigation may offer more explainability when working with machine learning algorithms in drought prediction studies, which could be critical for predicting future drought events.