Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Responses to Salt Stress

Responses to Salt Stress

Salt stress—which can be triggered by high salt concentrations in a plant’s environment—can significantly affect plant growth and crop production by influencing photosynthesis and the absorption of water and nutrients.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Temporal evolution of the environmental footprints of intensive farming across England.

PloS one·2026

Same author

Context matters: how river typology shapes biotic responses to fine sediment pressure.

Landscape ecology·2026

Same author

Intra-storm variations in the contributions of geological formations to suspended sediment: a comparison between Bayesian and FingerPro sediment fingerprinting methods.

Environmental science and pollution research international·2025

Same author

The number of phosphorus loss events will increase with variability and seasonality in far future climate scenarios.

Scientific reports·2025

Same author

Agricultural practices can threaten soil resilience through changing feedback loops.

NPJ sustainable agriculture·2025

Same author

A dataset of large ensemble of CMIP6-based transient climate scenarios for impact assessment in Great Britain.

Data in brief·2025

Same journal

Retraction Note: Toward a sustainable environment: nexus between geothermal energy growth and land use change in EU economies.

Environmental science and pollution research international·2026

Same journal

Retraction Note: COVID-19: pathogenesis, advances in treatment and vaccine development and environmental impact-an updated review.

Environmental science and pollution research international·2026

Same journal

Alkali-activated stabilization of lead-zinc tailings: mechanical performance, leaching behavior, and heavy metal immobilization mechanisms.

Environmental science and pollution research international·2026

Same journal

Integrated treatment of tannery wastewater by coagulation-flocculation and ultrasound-assisted photo-Fenton-like heterogeneous process using a valorized sludge-based catalyst: optimization of operational performance and toxicity assessment.

Environmental science and pollution research international·2026

Same journal

A review on recent advances in the environmental occurrence of benzothiazoles: analytical methods and their role as non-exhaust traffic tracers.

Environmental science and pollution research international·2026

Same journal

Ensemble model based on time series and regression to predict daily air quality in Tehran.

Environmental science and pollution research international·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Spatial modelling of soil salinity: deep or shallow learning models?

Aliakbar Mohammadifar¹, Hamid Gholami², Shahram Golzari^3,4

¹Department of Natural Resources Engineering, University of Hormozgan, Bandar-Abbas, Hormozgan, Iran.

Environmental Science and Pollution Research International

|March 24, 2021

Summary

This summary is machine-generated.

Deep learning models accurately predict soil salinity, outperforming traditional machine learning. This research recommends deep learning for environmental science predictions, crucial for land conservation against degradation.

Keywords:

Deep convolutional neural networks Deep learning models Shallow machine learning models Soil salinity spatial maps

More Related Videos

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

Related Experiment Videos

Last Updated: Nov 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

Area of Science:

Environmental Science
Geospatial Analysis
Machine Learning

Background:

Soil salinity is a major driver of land degradation and desertification.
Accurate spatial prediction of soil salinity is essential for effective land management and conservation strategies.

Purpose of the Study:

To predict soil salinity in the Jaghin basin, southern Iran.
To compare the performance of four deep learning (DL) models and six shallow machine learning (ML) models for soil salinity spatial mapping.
To identify the most effective modeling approach for soil salinity prediction in environmental science.

Main Methods:

Utilized 49 environmental variables derived from Landsat 8, including DEM-extracted covariates and soil-salinity indices.
Collected 319 soil samples to measure electrical conductivity (EC) for soil salinity assessment.
Applied and compared deep learning models (DCNNs, DenseDNNs, RNN-LSTM, RNN-GRU) and shallow ML models (BCART, cforest, cubist, QR-LASSO, RR, SVM).
Selected key features controlling soil salinity using a MARS model.
Assessed model performance using Taylor diagrams and Nash-Sutcliffe Efficiency (NSE).

Main Results:

Deep learning models demonstrated superior performance, achieving NSE values ≥ 0.9, with Deep Convolutional Neural Networks (DCNNs) being the most accurate (NSE = 0.96).
Shallow machine learning models achieved lower performance, with NSE values ≤ 0.83.
The study generated soil salinity spatial maps (SSSMs) using the best-performing DL models, showing predicted EC ranges from 0.67 to 14.73 dS/m (DCNNs).

Conclusions:

Deep learning models significantly outperform shallow machine learning models in generating accurate soil salinity spatial maps.
The findings support the recommendation of using deep learning approaches for soil salinity prediction in environmental science applications.
Accurate soil salinity mapping is vital for mitigating land degradation and desertification.