PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
June 20, 2026Chilean journal of agricultural researchOpen Access

Salinization evaluation in arable land using unmanned aerial vehicles, multispectral images, and machine learning

View Full Paper
Ask AI
Bookmark
Share

Authors

PHPatricia Paulina Hernández-VictoriaHFHéctor Flores-MagdalenoAQAbel Quevedo-Nolasco

Discussion

Loading...

Member takes

Overview

Randomized trial predicts soil salinity using unmanned aerial vehicles and machine learning, suggesting improved agricultural management practices.

Key Points

  • This work aims to predict soil salinity and sodicity using aerial images and machine learning techniques.
  • Collected 300 soil samples to measure electrical conductivity and exchangeable sodium percentage.
  • Used multispectral images from UAVs to calculate reflectance indices for predicting salinity.
  • Trained and validated five machine learning algorithms: Neural Networks, Random Forest, Support Vector Machine, Nearest Neighbors, and Decision Trees.
  • Random Forest model achieved 69% accuracy, 69% recall, and 39% kappa for predicting electrical conductivity categories.
  • Support Vector Machine provided 73% accuracy, 65% recall, and 41% kappa for predicting exchangeable sodium percentage.

Cite This Study

Hernández-Victoria et al. (2026) studied this question.

synapsesocial.com/papers/6a362e62db0793dc1a536170https://doi.org/10.4067/s0718-58392026000300369
View Full Paper
Ask AI
Bookmark
Share