It is with great pleasure that we present the latest issue of the International Journal of Space Applications, published by Pioneer Research Publications (P) Limited. This issue features five articles, comprising three research papers and two review articles, that advance current understanding in the domains of machine learning-based crop yield estimation, remote sensing image fusion, GNSS Reflectometry for soil moisture retrieval, and the application of deep learning for risk-aware agricultural planning.

This edition highlights the growing convergence of satellite remote sensing and machine learning models as powerful tools for agricultural forecasting and geospatial analysis. One study presents an ML framework for paddy yield prediction in Punjab and Haryana, using over four decades of agro-meteorological data and combining models with Monte Carlo simulations for probabilistic forecasting with quantified uncertainty intervals. A complementary article focuses on estimating wheat production across five Indian states, integrating Terra MODIS-derived products - such as NDVI, LAI, and thermal anomaly data - alongside GLDAS soil moisture over a 22-year period. With the growing need for accurate soil moisture data at high spatial and temporal resolutions, this issue also includes a review article on GNSS Reflectometry (GNSS-R), describing how reflected satellite navigation signals can be used to estimate soil moisture and other geophysical parameters across a range of land and ocean surface conditions. For early-career researchers navigating the complexities of machine learning pipelines, one article offers a practical, end-to-end guide to applying ML models to remote sensing data - covering data preprocessing, feature engineering, hyper-parameter tuning, and model evaluation, grounded in a wheat yield estimation case study. Finally, the issue presents a review of ten pixel-level image fusion techniques, comparing conventional methods such as Brovey Transform, IHS, and PCA with hybrid approaches including IHS-BT and PCA-HPF, and evaluates them using both visual and statistical criteria on multispectral and SAR data.

Taken together, the papers in this issue reflect a shared conviction that the challenges of food security, resource management, and environmental monitoring are effectively addressed through the integration of space-based observations with data-driven intelligence. With scales ranging up to national crop landscapes, and across sensors spanning optical, SAR, and navigation satellite systems, the contributions collectively demonstrate that timely, accurate, and probabilistic information derived from remote sensing can move the country’s agriculture toward a planned, policy-relevant decision support system that serves farmers, governments, and the global sustainability agenda alike.