Soil nitrogen (N) is a crucial nutrient for agricultural productivity and ecosystem health. The accurate and timely assessment of total soil N is essential for evaluating soil health. This study aimed to determine the impact of bootstrapping techniques on improving the predictive accuracy of indirect total soil N in conventional wheat fields in Al-Muthanna, Iraq. We integrated a novel methodological framework that integrated bootstrapped and non-bootstrapped total soil N data from 110 soil samples along with Landsat 9 imagery on the Google Earth Engine (GEE) platform. The performance of the proposed bootstrapping-enhanced random forest (RF) model was compared to standard RF models for soil N prediction, and outlier samples were analyzed to assess the impact of soil conditions on model performance. Principal components analysis (PCA) identified the key spectral reflectance properties that contribute to the variation in soil N. The PCA results highlighted NIR (band 5) and SWIR2 (band 7) as the primary contributors, explaining over 91.3% of the variation in soil N within the study area. Among the developed models, the log (B5/B7) model performed best in capturing soil N (R² = 0.773), followed by the ratio (B5/B7) model (R² = 0.489), while the inverse log transformation (1/log (B5/B7), R² = 0.191) exhibited the lowest performance. Bootstrapped RF models surpassed non-bootstrapped random forest models, demonstrating enhanced predictive capability for soil N. This study established an efficient framework for improving predictive capacity in areas characterized by limited, low-quality, and incomplete spatial data, offering valuable insights for sustainable nitrogen management in arid regions dominated by monoculture systems.

Crop burning is an age-old issue that is practiced by farmers mostly for clearing the fields. This practice causes environmental pollution ranging from reducing soil fertility to human health. This study utilized multi-geospatial processing platforms: Google Earth Engine (GEE) and Fire Information for Resource Management System (FIRMS) to derive Normalized burn ratio (NBR), and pre/post-fire ΔNBR for 2015 and 2023 to identify burnt fields and changes in burning practices. Further, the study relied upon on-field data to assess soil properties pre/post-fire date of 2023 in selected fields within Babil governorate. Overall, the study found that the leveraging of cloud-based geospatial platforms performed well in detecting burnt fields with a noticeable decrease in fire hotspots of 2023 when compared to 2015. The results of pre/post burning analysis soil samples showed that soil nutrients are declined. Among the measured soil properties, Nitrogen and soil organic matter are highly declined in average of 30% for nitrogen and 45% for O.M. While the average of decreasing in CEC and CaCO3 ranged from 5 to 15%. A slightly increased are observed for pH, salinity, Ca, Na, Mg, and Potassium. Open wheat field burning depletes soil organic matters and nutrients contents and away all the essential that make the topsoil healthy. The fire severity classification results indicated a dominant of low severity class over all selected Wheat-cultivated fields with value ranged from 22 to 86% of the burned area. A low correspondence was observed for low to moderate severity class with accuracy of 47.58%, suggesting high misidentification of these classes. Moreover, the study findings confirmed the effectiveness of utilizing multi- processing platforms approaches to overcome the misidentification of residue burnt fields.

Unplanned land use reflects the changes from agricultural to urbanization and decreasing of green spaces in cities and agricultural lands surrounding cities. The Soil Adjusted Vegetation Index (SAVI), Dry Bare - Soil Index (DBSI) and Normalized Difference Built-up Index (NDBI) indices were derived to evaluate the rate of the land use/cover changes due to uncontrolled urban sprawl for the years 2001 and 2020. Field indicators were also used to assess soil properties’ degradation by using Land Degradation Assessment in Drylands (LADA) under the FAO Global Environment Facility (GEF) project. A set of 30 soil samples were randomly collected from two locations: unplanned built-up and vegetated sites in Babil Governorate, Iraq. The results showed that soil texture and salinity were the most varied indicators. The poorer areas (unplanned urban areas) were low and assessed as poor quality, while the vegetated site was assessed as moderate quality with high total score values. The findings from spectral indices show a significant rise in the built-up land use/cover category, expanding from 10.367 square kilometres in 2001 to 50.883 square kilometres in 2020. In contrast, the areas of bare-soils and vegetated decreased from 29.29 and 35.474 square kilometres in 2001 to 12.511 and 19.601 square kilometres in 2020, respectively. Various analytical techniques proved instrumental in distinguishing the different land use/cover categories in this research.