Ten Billion Tree Tsunami Project Reveals Climate Change Mitigation and Precipitation Increase in Khyber Pakhtunkhwa Province, Pakistan

Climate change is a pressing global issue, potentially driven by LULC changes including deforestation, urbanization, and some other anthropogenic activities. The goal of our study was to evaluate the effectiveness of Ten Billion Tree Tsunami Project (TBTTP) in improving LULC and on regional climate change using machine learning. In this study, we utilized the Google Earth Engine platform, integrating multiple data sources such as Landsat 8 satellite imagery and Terra Climate datasets. A Random Forest machine learning classifier was employed to process the data, incorporating Landsat bands, vegetation indices (NDVI, EVI, NDWI), and environmental variables (precipitation, PDSI, slope). The impacts of TBTTP on Land Use Land Cover Changes (LULCC) and regional climate were analyzed for the pre-project (2015–2018) and post-project (2019–2023) periods. Our results indicated a significant 3.36% increase in forest area, demonstrating the effectiveness of coordinated reforestation projects in mitigating climate change and restoring ecological balance. Average annual LST rose by 0.137 °C during the pre-TBTTP period but fell by −0.0875 °C post-TBTTP. Some districts, such as Dera Ismail Khan, with the highest LST and least vegetation fractional area, clearly indicate a need for more forest land in that region. Post-TBTTP, precipitation increased by 15.33% and ET by 5.52%, indicates that the project successfully enhanced vegetation cover and forest health. These eco-friendly efforts have led to consistent forest growth, highlighting the need for better land use management, although more work is still required in districts like Bannu and Dera Ismail Khan. Therefore, the research findings provide a viable foundation to promote qualified reforestation projects such as TBTTP and also recognize the value of GEE in detecting long-term trends and promoting sustainable development.