The Northeast region of Thailand covers approximately 16.89 million hectares, with about 6.17 million hectares of seasonal rice cultivation and 2.85 million hectares affected by soil salinity—a major constraint to agricultural productivity in this region. This study develops an integrated data fusion framework combining multi-temporal Landsat-8 and Sentinel-2 imagery to train machine learning (ML) models for the prediction of rice yield and soil salinity, allowing for an analysis of their relationship. The field data comprised 380 rice yield and 625 soil electrical conductivity (EC) samples collected in 2023. Three ML models—Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Regression (SVR)—were applied for variable reduction and optimal predictor selection. RF achieved the highest accuracy for yield prediction (R² = 0.86, RMSE = 0.19 t ha⁻¹) and salinity estimation (R² = 0.93, RMSE = 0.87 dS/m) when using fused Landsat–Sentinel data. Spatial analysis of 5000 matched points showed a strong negative relationship between seedling stage EC and yield (R² = 0.71), with yields declining sharply above 5 dS/m and remaining below 1.5 t ha⁻¹ beyond 15 dS/m. These results demonstrate the potential of multi-sensor fusion and ensemble ML approaches for precise soil salinity monitoring and sustainable rice production.

Contemporarily, one of the most pressing concerns is reliable and rapid weather forecasting. In Nepal, the Department of Hydrology and Meteorological uses a numerical modeling approach to forecast the weather, which is tardy and requires high end equipment to process the information so deep learning approach will be best alternative. This project aims to forecast the next 2-hour Precipitation and Air Temperature for Pokhara Domestic Airport meteorological station and next day Precipitation, Maximum and Minimum air Temperature forecast for Lumle, Begnas and Lamachaur meteorological station, total of four meteorological stations of the Kaski District, Nepal using Long Short-Term Memory (LSTM): a Recurrent Neural Network (RNN) and deploy the outputs through the web portal. The four hourly parameters: Rainfall, Relative Humidity (R.H), Wind Speed and Air Temperature were used for modeling the airport station forecast whereas Rainfall, Relative Humidity (R.H), Maximum and Minimum Temperature were used for modeling the Begnas and Lumle station forecast and only Precipitation data was used for Lamachaur station. Averaging and linear interpolation techniques were used to fill out the missing values and outliers were detected using Box Plot and replaced with threshold value for each parameter. Stochastic Gradient Descent and Adam optimizer are used to optimize the LSTM model. Among all the models prepared, Root Mean Square Error (RMSE) values range from 0.58 to 4.08 for precipitation model and from 0.16 to 0.82 for air temperature model and Mean Absolute Error (MAE) values range from 0.21 to 2.87 for precipitation model and from 0.12 to 0.64 for air temperature model were the values of the final model that indicates better accuracy for air temperature. The R² values range from 0.89 to 0.99 indicating the train and test data were fitted to the model really well.

Accurate mapping of commercial durian plantations is essential for agricultural inventory, precision agriculture, and sustainable land management but remains challenging because of spectral similarity with other evergreen vegetation. This study developed a multisource remote sensing approach integrating multi-temporal Sentinel-2 imagery, Sentinel-1 Synthetic Aperture Radar (SAR), DEM-derived terrain variables, recursive feature selection, and machine learning for binary durian plantation classification in Sisaket Province, Thailand. A total of 2430 field reference samples were used to evaluate Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART). RF achieved the strongest overall performance using the integrated Sentinel-2, Sentinel-1, and DEM dataset, with an Overall Accuracy of 90.38%, an F1-score of 90.59%, a Kappa coefficient of 0.81, and an AUC of 0.991. Recursive feature selection reduced the predictor set from 53 to 12 variables (77.4%) while retaining high classification performance. The retained 12-predictor subset comprised nine Sentinel-2-derived variables (five seasonal EVI and four NDBI variables), two Sentinel-1 VV/VH ratio variables, and one DEM-derived elevation variable, corresponding to 75.0%, 16.7%, and 8.3% of the retained predictors, respectively. The proposed approach provides an accurate and computationally efficient method for durian plantation mapping within the study area, with broader applicability requiring further validation.

This research addresses challenges in satellite-derived Earth observation data, such as cloud cover, atmospheric condition, seasonality and calibration inconsistencies, by leveraging Synthetic Aperture Radar for cloud penetration and Generative Adversarial Networks (GANs) for cloud removal and image synthesis. The main objective of this research is to develop conditional GAN (cGAN) models capable of synthesizing multispectral images from SAR (Sentinel-1), Optical (Sentinel-2) images and DEM (SRTM 30). The research dataset consists of above three products downloaded for 10 locations distributed across different geographical regions of Nepal from 2022-2023. Using these dataset the cGAN models are trained with different configuration. An initial cGAN model by Bermudez saw improved performance with DEM inclusion and further enhanced by integrating an attention block in the residual block. Thus, attention cGAN (A_ cGAN) model was selected for further analysis. Among, the A_cGAN models the A_ cGAN_SOD model performed the best which uses the dataset (SAR, DEM and optical images) while comparing the MAE, RMSE, SSIM and PSNR values. The image generated from A_cGAN_SOD model for Hetauda was used for LULC classification using random forest algorithm obtaining the overall accuracy of 89.96% which shows that the model output is applicable.