article · The Egyptian Journal of Remote Sensing and Space Science
Precision agriculture relies on site-specific recommendations to optimise agricultural inputs across space and time. Satellite data from Landsat and MODIS-NDVI, combined with climate, topographic records, and laboratory soil samples, were used to map seven soil properties across Punjab, Pakistan, covering the period from 2000 to 2020. The assessed properties included soil texture, electrical conductivity, pH, nitrogen, phosphorus, potassium, and organic matter. Three models, namely support vector machine, random forest regression, and multiple linear regression, were evaluated against separate validation samples. Random forest regression consistently delivered the highest prediction accuracy, outperforming linear modelling by handling non-linear relationships. Analysis revealed that cultivated land fell from 43.16 percent in 2000 to 38.24 percent in 2020. Regional soils exhibited high salinity, organic matter below one percent, and low nitrogen, alongside adequate phosphorus and potassium.
Understanding soil health and declining cropland is essential for sustaining agricultural productivity. By demonstrating that freely available satellite imagery and machine learning can accurately map vital soil nutrients and salinity, this approach offers an affordable, low-cost way to monitor soil conditions and land use changes across broad agricultural regions without relying entirely on costly, labour-intensive ground sampling.
This work represents applied and tested research that could benefit precision agriculture service providers, farm managers, and regional planning bodies. The methodology demonstrates how freely available satellite data can be paired with machine learning to produce low-cost soil property maps for site-specific management. Moving this toward practical commercial use would require packaging the tested predictive models into operational software platforms or digital advisory tools for farmers.
AI-generated from the published abstract. Always read the original work before citing.
Precision agriculture which facilitates and enables crop management through site-specific recommendations, is essential to optimize agricultural inputs in space and time. In this study, we used Landsat and MODIS-NDVI product data with climatic, topographic data and laboratory-analyzed soil samples to map the spatial distribution of seven soil properties; soil texture (T), electrical conductivity (EC), potential hydrogen (pH), nitrogen (N), phosphorus (P), potassium (K), and organic matter (OM) in the Punjab, Pakistan from 2000 to 2020. We examined and compared three statistical prediction models: the support vector machine (SVM), the random forest regression (RFR), and the multiple linear regression (MLR). The predictions were validated against a separate set of soil samples while considering the modeling region and an extrapolation area. Model performance statistics showed that the RFR often provided the highest accuracy, with the machine learning algorithms performing slightly better than the MLR. It was discovered that one obstacle to accurately forecasting soil parameters at unsampled areas with MLR was its inability to handle non-linear connections between independent and dependent variables. The results indicate that the cultivated area decreased from 43.16 % in 2000 to 38.24% in 2020. The soil has a high level of EC due to salinity. In general, the soils contained < 1% OM with lower N. However, the K and P contents were considered medium and adequate. Free remote sensing data has made it possible to improve soil knowledge at local and regional scales in data like Punjab with little outlays of time and money.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.ejrs.2023.05.005
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
