Detecting Land Use Changes Using Hybrid Machine Learning Methods in the Australian Tropical Regions

Aug 3, 2026

Upload by Jiven

The study evaluates hybrid machine learning methods for detecting land use change with emphasis on agricultural land using remote sensing data processing. Two Landsat 8 spectral images are used to train and test a feed-forward neural network classifier. Evolutionary optimization is implemented via particle swarm optimization and invasive weed optimization during training, and three conventional backpropagation training schemes—LM, SCG, and BFG—are used for comparison. Results indicate evolutionary algorithms are less reliable due to accuracy and computational complexity constraints. BFG and LM outperform the evolutionary options for agricultural land detection, with BFG slightly more robust and LM potentially preferable for low computational cost projects.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

Land use/land cover and remote sensing motivation

Change detection methods and categories

Neural networks and feed-forward training background

GeoJournal [https://doi.org/10.1007/s10708-022-10678-5](https://doi.org/10.1007/s10708-022-10678-5) Detecting land use changes using hybrid machine learning methods in the Australian tropical regions Mahdi Sedighkia · Bithin Datta Accepted: 6 May 2022 © The Author(s) 2022 Abstract The present study evaluates the application of the hybrid machine learning methods to detect changes of land use with a focus on agricultural lands through remote sensing data processing. Two spectral images by Landsat 8 were applied to train and test the machine learning model. Feed forward neural network classifier was utilized as the machine learning model in which two evolutionary algorithms including particle swarm optimization and invasive weed optimization were applied for the training process. Moreover, three conventional training methods including Levenberg–Marquardt back propagation (LM), Scaled conjugate gradient backpropagation (SCG) and BFGS quasi-Newton backpropagation (BFG) were used for comparing the robustness and reliability of the evolutionary algorithms. Based on the results in the case study, evolutionary algorithms are not a reliable method for detecting changes through the remote sensing analysis in terms of accuracy and computational complexities. Either BFG or LM is the best method to detect the agricultural lands in the present study. BFG is slightly more robust than the LM method. However, LM might be preferred for applying in the projects due to low computational complexities. M. Sedighkia (*) · B. Datta College of Science and Engineering, James Cook University, Townsville, Australia [e-mail: Mahdi.sedighkia@my.jcu.edu.au](e-mail: Mahdi.sedighkia@my.jcu.edu.au) Keywords Particle swarm optimization · Invasive weed optimization · Back propagation · Neural network classifier · Remote sensing Introduction Land use/ Land cover (LULC) maps are highly applicable for economic evaluation of land resources and hydrological studies (Spruce et al., 2018) . Hence, generating land use maps have been highlighted in the literature from many years ago (Fallati et al., 2017) . Increasing population in recent decades affect the land use in different countries. In fact, quick change of the land use might be a challenge in the projects that means updating the LULC map is essential Traditional methods for surveying LULC might be expensive and arduous that means they are not utilizable for quick update of the land use maps (Cienciała et al., 2021) . Hence, novel methods have been highlighted in recent decades. One of the applicable and efficient methods to update the land use map for different urban and non-urban areas is remote sensing data processing. Many previous studies corroborated the applicability of the remote sensing analysis to detect the LULC (Liping et al., 2018) . Due to focus of the present study on using remote sensing for monitoring LULC, it is necessary to have review on the remote sensing analysis and related methods. Several satellites with different sensors have been launched in recent decades for remote sensing 1 3 purposes reviewed by (Zhu et al., 2018) . In fact, these satellites are able to capture the spectral images from the lands and oceans that could be utilized in a wide range of projects and studies. Different methods have been proposed for change detection including Image Differencing, Image Ratioing, Change Vector Analysis, Principal Component Analysis, Chi-Square Transformation, Post-Classification Comparison, Artificial Neural Networks (ANNs) and Hybrid Change Detection (Full review on methods by Alqurashi & Kumar, 2013) . Change detection techniques for remote sensing applications are categorized to five classes including algebra based change detection, transform based change detection, classification based change detection, Geographical information system based methods and advanced methods (Asokan & Anitha, 2019) . Three popular algebra based models include image differencing (Ke e

FAQs

What remote sensing data and model are used to detect land use changes?

Two Landsat 8 spectral images are processed to train and test a feed-forward neural network classifier for land use change detection with a focus on agricultural lands.

How are evolutionary algorithms and conventional backpropagation methods compared?

Particle swarm optimization and invasive weed optimization are applied in the training process, while LM, SCG, and BFG backpropagation are used as conventional baselines to compare robustness and reliability.

Which training approaches perform best for agricultural land detection?

BFG or LM are the best methods in the case study. BFG is slightly more robust than LM, while LM may be preferred in projects due to lower computational complexity.

Aug 3, 2026

Upload by Jiven