Land surface temperature prediction with dual satellites and BPNN: a comparative transfer function analysis

Abstract

ABSTRACT Driven by global sustainability goals, understanding land surface temperature (LST) in urban thermal environments (UTE) is crucial. This study analyses remotely sensed LST data from Aqua and Terra satellites in a rapidly growing non-tier Indian city. It uniquely integrates remote sensing and soft computational analysis to predict daytime LST using artificial neural networks (ANN). The study is categorized based on transfer functions and hyper-parameters to enhance the comprehension of LST prediction and simulation scenarios by employing Back Propagation Neural Network (BPNN) model. Results indicate that the tansig transfer function yields the best performance overall in Aqua and Terra LST prediction, while purelin performs the least effectively. This study provides evidence that soft computing techniques effectively estimate LST data, offering a valuable solution for data scarcity issues. However, the findings are specific to the study area and may vary elsewhere. Exploring alternative methods and incorporating data from other areas could potentially improve accuracy and overall performance. Future research could focus on investigating the mechanisms behind different methods and their interactions with various factors. Additionally, integrating other variables like vegetation index, soil moisture, and others could contribute to a more holistic understanding of LST dynamics and enhance predictive capabilities.