Long Short-Term Memory (LSTM)-based prediction of heatwave trends in northwestern Nigeria

Climate change has accelerated devastating impacts across the globe, and heatwaves are among the most severe climate extremes threatening human health, agricultural productivity, and ecosystems in northwestern Nigeria. This study aimed to develop a long short-term memory (LSTM) based model to predict heatwave trends in northwestern Nigeria. Historical meteorological data, including daily maximum temperature, minimum temperature, and relative humidity from 1980 to 2024, were sourced from the Nigerian Meteorological Agency (NiMet). Heatwave intensity was measured via heat index (HI) computation, whereas temporal trends were analyzed via the Modified Mann Kendall (MMK) test and Innovative Trend Analysis (ITA). Spatial variation in heatwave intensity was mapped via the Inverse Distance Weighting (IDW) method. The LSTM model demonstrated high predictive accuracy during the testing phase, with correlation coefficients (R) ranging from 0.87 to 0.91 and coefficients of determination (R 2 ) ranging from 0.76 to 0.83. The findings revealed a pronounced increase in the frequency and severity of heatwaves across northwestern Nigeria. These findings demonstrate the ability of LSTM based forecasting to provide reliable heatwave predictions and highlight the potential of LSTM models for supporting regional climate adaptation strategies, heat early warning systems, and evidence-based decision making.