A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data
Authors:
- Olzhas NuridinovONOlzhas Nuridinov
- Gulzira AbdikerimovaGAGulzira Abdikerimova
- Dinara KaibassovaDKDinara Kaibassova
- Amir OrazbayAOAmir Orazbay
- Zeinigul SattybayevaZSZeinigul Sattybayeva
- Akbota YerzhanovaAYAkbota Yerzhanova
- Ainur OrynbayevaAOAinur Orynbayeva
- Gulkiz ZhidekulovaGZGulkiz Zhidekulova
- Aigul KubegenovaAKAigul Kubegenova
Open Access
- 8 July 2026
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 14 (7) , 418
Abstract
This paper proposes a hybrid, interpretable machine learning framework for the preliminary screening of soil macronutrients using Sentinel-2 and AgroLens data. This study aims not to replace laboratory analysis, but to test the feasibility of obtaining a useful proxy signal for estimating nitrogen (N), phosphorus (P), and potassium (K) content using a limited set of remote sensing and agricultural features. The developed pipeline includes data auditing, leakage control, feature engineering, train-only normalization, group-aware partitioning, baseline/SOTA model comparison, hybrid regression modeling, SHAP interpretation, and uncertainty assessment. The experiment used 4471 AgroLens observations and 126 features derived from Sentinel-2 spectral aggregates, vegetation indices, temporal characteristics, and crop-related parameters. The evaluation indicated that the proposed approach consistently improves forecasting quality relative to baseline models under reduced-input conditions. Linear relationships between target variables ranged from 0.14 to 0.17, while nonlinear relationships reached 0.23. SHAP analysis revealed significant contributions from vegetation indices, crop-specific interactions, and Sentinel-2 spectral channels. The findings support the applicability of the proposed framework for preliminary monitoring, prioritizing field surveys, and decision support in digital agriculture. Although an additional AgroLens control segment was used to assess the robustness of the study, the study did not include independent external validation of the data collected across different geographic or agro-climatic conditions.Keywords
This publication has 24 references indexed in Scilit:
- Key Determinants of Soil Erosion: Insights Using Machine Learning Algorithm2026
- A novel resilient agro-ecological system for sustainable urban-rural agricultural integrationSustainable Cities and Society, 2025
- Toward Transparent and Reproducible Machine Learning–Based Research in Urban Water NetworksJournal of Water Resources Planning and Management, 2025
- Comparative Analysis of the Hybrid Mamba and Transformer Models for Intelligent Pest Prediction2025
- Soil and crop interaction analysis for yield prediction with satellite imagery and deep learning techniques for the coastal regionsJournal of Environmental Management, 2025
- Automatic Prediction of Soil Moisture Using Efficient Convolutional Neural Network from the Synthetic-Aperture Radar DataRemote Sensing in Earth Systems Sciences, 2025
- Multiscale adaptive PolSAR image superpixel generation based on local iterative clustering and polarimetric scattering featuresISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Analyzing Disease and Pest Dynamics in Steppe Crop Using Structured DataIEEE Access, 2024
- Smart solutions for capsicum Harvesting: Unleashing the power of YOLO for Detection, Segmentation, growth stage Classification, Counting, and real-time mobile identificationComputers and Electronics in Agriculture, 2024
- Machine learning and remote sensing techniques applied to estimate soil indicators – ReviewEcological Indicators, 2022