A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data

Nuridinov, Olzhas; Abdikerimova, Gulzira; Kaibassova, Dinara; Orazbay, Amir; Sattybayeva, Zeinigul; Yerzhanova, Akbota; Orynbayeva, Ainur; Zhidekulova, Gulkiz; Kubegenova, Aigul

doi:10.3390/technologies14070418

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data

by

Olzhas Nuridinov

¹,

Gulzira Abdikerimova

^1,*

,

Dinara Kaibassova

^2,*

,

Amir Orazbay

¹

,

Zeinigul Sattybayeva

³,

Akbota Yerzhanova

^4,*,

Ainur Orynbayeva

⁵,

Gulkiz Zhidekulova

⁶ and

Aigul Kubegenova

⁷

¹

Department of Information Systems, L. N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan

²

School of Software Engineering, Astana IT University, Astana 010000, Kazakhstan

³

Department of Agriculture and Bioresources, Agrotechnical Institute, Sh. Ualikhanov Kokshetau University, Kokshetau 020000, Kazakhstan

⁴

Groups of Educational Programs (GEP), Agroengineering, Mechanics and Metalworking, Institute of Engineering and Food Technology, Kazakh Agrotechnical Research University Named After S. Seifullin, Astana 010000, Kazakhstan

⁵

Department of Epidemiology and Biostatistics, Astana Medical University, Astana 010000, Kazakhstan

⁶

Department of Cybersecurity and Cryptology, Farabi Kazakh University, Almaty 010002, Kazakhstan

⁷

Department of Computer Science, Institute of Business and Digital Technologies, Kazakh Agrotechnical Research University Named After S. Seifullin, Astana 010000, Kazakhstan

^*

Authors to whom correspondence should be addressed.

Technologies 2026, 14(7), 418; https://doi.org/10.3390/technologies14070418

Submission received: 27 May 2026 / Revised: 4 July 2026 / Accepted: 5 July 2026 / Published: 8 July 2026

Download Versions Notes

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: Sentinel-2; AgroLens; soil nutrient screening; explainable machine learning; hybrid modeling; precision agriculture

Share and Cite

MDPI and ACS Style

Nuridinov, O.; Abdikerimova, G.; Kaibassova, D.; Orazbay, A.; Sattybayeva, Z.; Yerzhanova, A.; Orynbayeva, A.; Zhidekulova, G.; Kubegenova, A. A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data. Technologies 2026, 14, 418. https://doi.org/10.3390/technologies14070418

AMA Style

Nuridinov O, Abdikerimova G, Kaibassova D, Orazbay A, Sattybayeva Z, Yerzhanova A, Orynbayeva A, Zhidekulova G, Kubegenova A. A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data. Technologies. 2026; 14(7):418. https://doi.org/10.3390/technologies14070418

Chicago/Turabian Style

Nuridinov, Olzhas, Gulzira Abdikerimova, Dinara Kaibassova, Amir Orazbay, Zeinigul Sattybayeva, Akbota Yerzhanova, Ainur Orynbayeva, Gulkiz Zhidekulova, and Aigul Kubegenova. 2026. "A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data" Technologies 14, no. 7: 418. https://doi.org/10.3390/technologies14070418

APA Style

Nuridinov, O., Abdikerimova, G., Kaibassova, D., Orazbay, A., Sattybayeva, Z., Yerzhanova, A., Orynbayeva, A., Zhidekulova, G., & Kubegenova, A. (2026). A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data. Technologies, 14(7), 418. https://doi.org/10.3390/technologies14070418

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

A Reproducible Hybrid AI Framework for Early Soil Nutrient Screening from Sentinel-2 Remote Sensing Data

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI