GWR–ANN modelling for spatiotemporal prediction of land surface temperature in Thanjavur delta: evaluating environmental impacts on climate action and SDGs

The concept of elevated Global Temperature influences the environment and induces a major impact on Climate Change. This research explores the interactions between environmental parameters and Land Surface Temperature fluctuations in Thanjavur District, Tamilnadu, India during the peak vegetative phases of the Kuruvai and Samba Seasons with three-year intervals between 2001 and 2023. The study examines the impact of variables such as soil texture, topography, land use and land cover, spectral indices, and meteorological parameters on land surface temperature patterns by analyzing data from multiple sources, including meteorological records, field data, Shuttle Radar Topography Mission Digital Elevation Model, and Landsat 5, 7, 8 imageries. The findings indicate that the land surface temperature has induced significant spatio-temporal changes in the Thanjavur delta. The Geographically Weighted Regression model is used to explore spatial distribution, which gives the best fit with a Moran’s I value of 0.38 for Kuruvai and 0.36 for Samba, indicating a clustered pattern in the land surface temperature distribution. Furthermore, the research employs Artificial Neural Networks to forecast future land surface temperature trends under various climate scenarios for the years 2030, 2040, and 2050. Kuruvai exhibits a 2–4 ℃ temperature rise, while Samba displays a moderate increase above 2 ℃, impacting various land cover areas. The study suggests the necessity for sustainable land management and climate adaptation strategies in the region. This work provides valuable insights for policymakers, urban planners, agronomists, and environmental scientists who are involved in the fields of sustainable development and climate resilience. Graphical abstract