Rapid prediction of soil hydraulic and physicochemical properties using the Nix Pro color sensor
Cheshmberah, Fatemeh ; Zolfaghari, Ali A. ; Taghizadeh-Mehrjardi, Ruhollah and Berndtsson, Ronny LU
(2026)
In Geoderma Regional
44.
- Abstract
Color is the most obvious and easily determined soil property that can provide crucial information about soil composition. The NIX™ Pro color sensor (Nix) presents a user-friendly alternative to the traditional Munsell manual method, with reduced sensitivity to environmental and human factors. Therefore, a new method was developed to use Nix in combination with machine learning to quickly and affordably estimate improved physical, hydraulic, and chemical soil properties. This study extends the application of the Nix sensor from chemical properties to include soil hydraulic properties, providing a rapid, reproducible, and practical prediction tool. The Nix and the Random Forest (RF) algorithm were employed to analyze the spectra of 150... (More)
Color is the most obvious and easily determined soil property that can provide crucial information about soil composition. The NIX™ Pro color sensor (Nix) presents a user-friendly alternative to the traditional Munsell manual method, with reduced sensitivity to environmental and human factors. Therefore, a new method was developed to use Nix in combination with machine learning to quickly and affordably estimate improved physical, hydraulic, and chemical soil properties. This study extends the application of the Nix sensor from chemical properties to include soil hydraulic properties, providing a rapid, reproducible, and practical prediction tool. The Nix and the Random Forest (RF) algorithm were employed to analyze the spectra of 150 soil samples collected from 0 to 30 cm depth in semi-arid regions of Iran. The results indicated that using the RF algorithm with CIE L*a*b* Color System data from the Nix, the best predictive performance was observed for CaCO₃ (R2 = 0.62, RMSE = 2.25) and field capacity (FC) (R2 = 0.50, RMSE = 4.99). Predictions for clay (R2 = 0.59, RMSE = 7.26), permanent wilting point (PWP) (R2 = 0.62, RMSE = 2.04), and sand (R2 = 0.49, RMSE = 10.08) also showed good agreement with measured values. Bulk density (BD) (R2 = 0.45, RMSE = 0.11) and soil available water (SAW) (R2 = 0.51, RMSE = 4.97) predictions exhibited higher errors relative to the observed ranges. The findings indicate that the Nix sensor's portability and cost-effectiveness, along with the RF algorithm, make it a practical tool for field applications. It provides quick, reliable, and improved estimates of CaCO₃ and FC, with good performance also observed for clay, PWP, and sand. The results reflect the method's efficacy, its possible adaptation to other areas with proper adjustment, and its integration into precision agriculture and environmental applications.
(Less)
- author
- Cheshmberah, Fatemeh
; Zolfaghari, Ali A.
; Taghizadeh-Mehrjardi, Ruhollah
and Berndtsson, Ronny
LU
- organization
- publishing date
- 2026-03
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Boruta algorithm, CIE L*a*b* color system, Hydraulic soil properties, Random forest
- in
- Geoderma Regional
- volume
- 44
- article number
- e01064
- pages
- 10 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:105030952894
- ISSN
- 2352-0094
- DOI
- 10.1016/j.geodrs.2026.e01064
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2026 Elsevier B.V.
- id
- f6dc8b71-867e-4298-9a0f-6e9fbf13c771
- date added to LUP
- 2026-03-17 17:26:45
- date last changed
- 2026-03-20 02:51:39
@article{f6dc8b71-867e-4298-9a0f-6e9fbf13c771,
abstract = {{<p>Color is the most obvious and easily determined soil property that can provide crucial information about soil composition. The NIX™ Pro color sensor (Nix) presents a user-friendly alternative to the traditional Munsell manual method, with reduced sensitivity to environmental and human factors. Therefore, a new method was developed to use Nix in combination with machine learning to quickly and affordably estimate improved physical, hydraulic, and chemical soil properties. This study extends the application of the Nix sensor from chemical properties to include soil hydraulic properties, providing a rapid, reproducible, and practical prediction tool. The Nix and the Random Forest (RF) algorithm were employed to analyze the spectra of 150 soil samples collected from 0 to 30 cm depth in semi-arid regions of Iran. The results indicated that using the RF algorithm with CIE L*a*b* Color System data from the Nix, the best predictive performance was observed for CaCO₃ (R<sup>2</sup> = 0.62, RMSE = 2.25) and field capacity (FC) (R<sup>2</sup> = 0.50, RMSE = 4.99). Predictions for clay (R<sup>2</sup> = 0.59, RMSE = 7.26), permanent wilting point (PWP) (R<sup>2</sup> = 0.62, RMSE = 2.04), and sand (R<sup>2</sup> = 0.49, RMSE = 10.08) also showed good agreement with measured values. Bulk density (BD) (R<sup>2</sup> = 0.45, RMSE = 0.11) and soil available water (SAW) (R<sup>2</sup> = 0.51, RMSE = 4.97) predictions exhibited higher errors relative to the observed ranges. The findings indicate that the Nix sensor's portability and cost-effectiveness, along with the RF algorithm, make it a practical tool for field applications. It provides quick, reliable, and improved estimates of CaCO₃ and FC, with good performance also observed for clay, PWP, and sand. The results reflect the method's efficacy, its possible adaptation to other areas with proper adjustment, and its integration into precision agriculture and environmental applications.</p>}},
author = {{Cheshmberah, Fatemeh and Zolfaghari, Ali A. and Taghizadeh-Mehrjardi, Ruhollah and Berndtsson, Ronny}},
issn = {{2352-0094}},
keywords = {{Boruta algorithm; CIE L*a*b* color system; Hydraulic soil properties; Random forest}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Geoderma Regional}},
title = {{Rapid prediction of soil hydraulic and physicochemical properties using the Nix Pro color sensor}},
url = {{http://dx.doi.org/10.1016/j.geodrs.2026.e01064}},
doi = {{10.1016/j.geodrs.2026.e01064}},
volume = {{44}},
year = {{2026}},
}