• Home
  • Search
  • Comparative Study of NIR-Based Machine Learning for Predicting Soil Nutrients in Indonesian Farmlands
  • https://doi.org/10.2478/ata-2026-0004Copy DOI Icon

Comparative Study of NIR-Based Machine Learning for Predicting Soil Nutrients in Indonesian Farmlands

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract This study evaluates the efficacy of machine learning models for predicting soil nitrogen (N), phosphorus (P), and potassium (K) concentrations from near-infrared (NIR) spectral data (750–2499 nm). A comparative analysis was conducted on models from three distinct categories: linear-based, non-linear kernel-based, and neural network-based, using data from 145 soil samples collected across four Indonesian provinces. Regularised linear modelling performed best: Ridge Regression achieved R ²/MAE of 0.999/0.00005% for N-Total, 0.868/0.01408% for P-Total, and 0.763/0.01239% for K-Total. The non-linear SVR delivered moderate fit ( R ² = 0.821 for N-Total) but produced the lowest MAE for K (0.00829%) at lower explained variance ( R ² = 0.419). Neural network-based models underperformed the linear baselines. This study demonstrates that, for this dataset, a simpler regularised linear model outperformed more complex architectures, underscoring the critical role of rigorous model selection in developing accurate spectroscopic tools for precision agriculture. Future research could explore hybrid or ensemble methods to combine the strengths of different model types, potentially improving prediction accuracy and robustness.

Similar Papers
  • Research Article
  • Citations3

Soil carbon and nutrient variations in an arable-ley rotation with organic pig production

  • Oct 27, 2021
  • Biological Agriculture & Horticulture
  • Benhua Sun +2
  • Research Article
  • Citations23

Near infrared spectroscopic imaging assessment of cartilage composition: Validation with mid infrared imaging spectroscopy

  • Apr 25, 2016
  • Analytica Chimica Acta
  • Uday P Palukuru +5
  • Research Article
  • Citations75

The Potential of near Infrared Reflectance Spectroscopy as a Tool for the Chemical Characterisation of Agricultural Soils

  • Mar 01, 2001
  • Journal of Near Infrared Spectroscopy
  • M Confalonieri +5
  • Research Article
  • Citations44

Spatial variability in surface sediment composition characterised by near-infrared (NIR) reflectance spectroscopy

  • Jan 01, 1999
  • Journal of Paleolimnology
  • Tom Korsman +3
  • Research Article
  • Citations32

Artificial intelligence approach based on near-infrared spectral data for monitoring of solid-state fermentation

  • Jul 18, 2016
  • Process Biochemistry
  • Augusto César Barchi +8
  • Book Chapter

Transformation of Phosphorus in Soils of Agroecosystems in Long-Term Experiments: Sustainability Challenges of Phosphorus and Food

  • Nov 25, 2020
  • Rafail A Afanas’Ev +2
  • Research Article
  • Citations29

Noise reduction for near-infrared spectroscopy data using extreme learning machines

  • Dec 29, 2018
  • Engineering Applications of Artificial Intelligence
  • Pablo A Henríquez +1
  • Research Article
  • Citations1

Using of NDVI in digital mapping of phosphorus content in soils and assessment of it's availability by plants

  • May 21, 2019
  • Исследования Земли из Космоса
  • N V Gopp +4
  • Research Article
  • Citations18

Effects of different green manure treatments on soil apparent N and P balance under a 34-year double-rice cropping system

  • Jun 04, 2018
  • Journal of Soils and Sediments
  • Xi Hong +9
  • Research Article
  • Citations4

Effects of Treated Wastewater on Soil Recovery in Degraded Semiarid Region

  • Dec 19, 2019
  • Journal of Experimental Agriculture International
  • Emanoel Lima Martins +3
  • Research Article
  • Citations28

Application of vibrational spectroscopy in the quality assessment of Buchu oil obtained from two commercially important Agathosma species (Rutaceae)

  • Sep 03, 2010
  • South African Journal of Botany
  • M Sandasi +3
  • Research Article

A Study of Physio-Chemical Properties of Healthy and Declined Nagpur Mandarin Orchards

  • Mar 01, 2020
  • International Research Journal of Science and Technology
  • Prashant Joshi +3
  • Research Article

Optical sensor characterization for rapid detection of nitrogen phosphorus and potassium concentrations in soil

  • Mar 10, 2026
  • Discover Sensors
  • Mangeh Elsie Jaja +5
  • Research Article
  • Citations3

Non-destructive spectroscopy-based technologies for meat and meat product discrimination - A review.

  • Oct 01, 2025
  • Meat science
  • Sara León-Ecay +3
  • PDF
  • Research Article

Environmental Analysis of Switchgrass on Soil

  • Aug 01, 2015
  • Universal Journal of Chemistry
  • Gija Geme +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.