<p>The agriculture sector is responsible for the majority of food production in Bangladesh. However, rapid urbanization and various anthropogenic factors have accelerated the rate of climate change, posing a significant threat to food security. This study utilizes a remote sensing-driven methodology to assess the potential impacts of climate change on food security in Bangladesh, with a specific focus on rice production. High-resolution Sentinel-1 imagery was used within the Google Earth Engine (GEE) platform to classify rice yield patterns, focusing on major growing seasons (Aman, Aus, Boro) for the years 2018, 2020, and 2022. For classification, Random Forest algorithm was selected over Support Vector Machine due to its superior performance and employed for further analyses. Subsequently, an Artificial Neural Network model (Multi-Layer Perceptron) was used within MOLUSCE to predict future yield dynamics for the years 2026 and 2030. Among the climatic variables, precipitation, evapotranspiration, soil moisture, sunshine duration, and cloud cover were integrated with three topographic variables: DEM, slope, and aspect, to assess their influence on rice productivity. The rice yield classification achieved a high degree of precision (AUC = 0.968). The analysis reveals a significant decline in rice cultivation area, from 519,318 hectares in 2018 to 442,902 hectares in 2022, with projected reductions to 421,697 hectares by 2026 and 357,145 hectares by 2030. Correlation analysis indicated a strong positive association between rice yield and sunshine (<i>r</i> = 0.70), a weaker positive correlation with precipitation (<i>r</i> = 0.26), and a moderate negative relationship with evapotranspiration (<i>r</i> = -0.32), while the remaining variables showed insignificant correlations. This study highlights the increasing vulnerability of rice production to climate change and emphasizes the need for acknowledging these effects. The developed method can contribute to improved crop mapping and early prediction of food security situations in the South Asian region.</p> Graphical Abstract <p>The graphical abstract illustrates a remote sensing and machine learning based approach to model and predict the impacts of climate change on rice production and food security in Bangladesh. The analysis focused on capturing three major rice growing seasons for Bangladesh: Aman, Aus, Boro from sentinel-1 imagery for the years 2018, 2020 and 2022. Random forest algorithm was used to classify rice yield which achieved a high classification accuracy (AUC = 0.968). A range of climatic (precipitation, evapotranspiration, soil moisture, sunshine duration and cloud cover) and topographic variables (DEM, slope and aspect) were pre-processed and mapped to identify their impact on rice production. The Pearson correlation coefficient analysis showed that there is a strong positive correlation between rice yield and sunshine (<i>r</i> = 0.70), a weaker positive correlation with precipitation (<i>r</i> = 0.26) and a moderate negative correlation with evapotranspiration (<i>r</i> = -0.32). For the prediction of future rice production dynamics, an Artificial Neural Network (ANN) model was utilized, projecting rice yield maps for 2026 and 2030. The research predicts a significant decline in rice production area, dropping from 519,318 hectares in 2018 to a projected 357,145 hectares in 2030. These findings highlight the increasing vulnerability of rice production under climate change. This methodology offers a comprehensive framework for crop mapping and early prediction of food security, potentially for the South Asian region.</p>