Spatial intelligence in AI applications for assessing soil health to monitor farming systems and associated ESG risk

Senanayake, S; Pradhan, B; Wedathanthirige, H

Spatial intelligence in AI applications for assessing soil health to monitor farming systems and associated ESG risk

Senanayake, S Pradhan, B

Wedathanthirige, H

Permalink

Publisher:: Elsevier
Publication Type:: Chapter
Citation:: Intelligence Systems for Earth, Environmental and Planetary Sciences: Methods, Models and Applications, 2024, pp. 81-111
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	23503410_15749305200005671.pdf	Published version	4.54 MB		View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Senanayake, S
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054
dc.contributor.author	Wedathanthirige, H
dc.date.accessioned	2024-11-18T01:16:37Z
dc.date.available	2024-11-18T01:16:37Z
dc.date.issued	2024-01-01
dc.identifier.citation	Intelligence Systems for Earth, Environmental and Planetary Sciences: Methods, Models and Applications, 2024, pp. 81-111
dc.identifier.isbn	9780443132933
dc.identifier.uri	http://hdl.handle.net/10453/181942
dc.description.abstract	Humans and many other living beings survive, thanks to healthy soils on the Earth's surface. However, soil health has been degrading for various reasons, such as human interference, natural disasters, and climate change. This study executes various spatial intelligence tools for monitoring and predicting soil erosion in farming systems concerning soil health for sustainable land management. The shared socioeconomic pathways (SSPs) of climate scenarios were combined with artificial neural networks (ANNs), random forest (RF), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS) models to predict the soil erosion vulnerability by 2050. The long short-term memory (LSTM) based deep learning tool was integrated with the revised universal soil loss equation (RUSLE) for continuous observation and prediction of soil erosion. Results indicate that farming systems WU2, IU2, IM1a, and IM1c have higher rates of soil erosion (>8t/ha/year) and will be highly vulnerable to soil deterioration by 2050. The findings support index-based crop insurance schemes, environmental, social, and governance (ESG) agricultural risk assessment in farming systems and achieving sustainable development goals (SDGs).
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Intelligence Systems for Earth, Environmental and Planetary Sciences: Methods, Models and Applications
dc.relation.isbasedon	10.1016/B978-0-443-13293-3.00001-4
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Spatial intelligence in AI applications for assessing soil health to monitor farming systems and associated ESG risk
dc.type	Chapter
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Transport Research Centre (TRC)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Advanced Modelling and Geospatial lnformation Systems (CAMGIS)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Transport Research Centre (TRC)/Associate Member
utslib.copyright.status	closed_access	*
dc.date.updated	2024-11-18T01:16:36Z
pubs.publication-status	Published

Abstract:

Humans and many other living beings survive, thanks to healthy soils on the Earth's surface. However, soil health has been degrading for various reasons, such as human interference, natural disasters, and climate change. This study executes various spatial intelligence tools for monitoring and predicting soil erosion in farming systems concerning soil health for sustainable land management. The shared socioeconomic pathways (SSPs) of climate scenarios were combined with artificial neural networks (ANNs), random forest (RF), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS) models to predict the soil erosion vulnerability by 2050. The long short-term memory (LSTM) based deep learning tool was integrated with the revised universal soil loss equation (RUSLE) for continuous observation and prediction of soil erosion. Results indicate that farming systems WU2, IU2, IM1a, and IM1c have higher rates of soil erosion (>8t/ha/year) and will be highly vulnerable to soil deterioration by 2050. The findings support index-based crop insurance schemes, environmental, social, and governance (ESG) agricultural risk assessment in farming systems and achieving sustainable development goals (SDGs).

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/181942