Monitoring and Assessment of Agri-Urban Land Conversion Using Multi-Sensor Remote Sensing and Gis Techniques

Abstract

Abstract. Continuous agricultural land conversion poses threat to food security but this has not been monitored due to ineffectual policies. One of the Philippine provinces with a high rate of conversion is the rice-producing province of Cavite. To assess the spatiotemporal dynamics of agricultural land conversion in Cavite, this study aims to develop an operational methodology to produce Land Use and Land Cover (LULC) change maps using a multi-sensor remote sensing approach for decision making and planning. LULC maps were generated using Random Forest Classification of Landsat 8 and Sentinel-1 image collections. Spectral indices, combinations of radar polarizations (VV, VH), and their principal components were included to improve its accuracy. Conversion maps were generated by taking the bi-annual difference of LULC maps from 2016 to 2019. Accuracy was assessed using visual inspection with Google Earth Pro. Classification was carried out using single-sensor (optical or radar) and multi-sensor (optical and radar) approach in combination with three feature selection algorithms, namely, Sandri and Zuccolotto (2006), Liaw and Wiener (2015), Kursa and Rudnicki (2010). Multi-sensor and single sensor yielded similarly high overall accuracies (OA = 96%) with the exception of single-sensor radar approach (OA = 53%). Multi-sensor approaches exhibit high accuracies (Cumulative Accuracy = 91%) in detecting agricultural to built-up LULC change up to 5,000 square meters unlike single-sensor optical approach (Cumulative Accuracy = 76%). Among the multi-sensor approaches, the method of Liaw and Wiener (2015) remains to be superior as it only uses eight (8) variables.

Land Cover Change Analysis of Carrascal, Madrid and Cantilan Mining Sites in Surigao Del Sur Using Remote Sensing

“…In the study of Talukdar et al (2020), machine learning algorithms for image classification were tested which resulted in Random Forest (RF) obtaining highest accuracy of 0.89 which suggests that it is the best LULC classifier. Moreover, aside from being non-parametric and flexible to highly dimensional data, RF could produce consistent accuracies compared to other algorithms (Talukdar et al, 2020;Torbick et al, 2016;Pelletier et al, 2016;Fargas et al, 2021). However, in the study of Basheer et al (2022), SVM was reported to perform better than RF in terms of overall accuracy.…”

“…The study of Fargas et al (2021) which developed an agri-urban land conversion monitoring using post classification change detection technique was also adopted in this study. Their study utilized Random Forest algorithm to produce LULC maps of their agriculture-dominant area for 3 different years and agriurban conversion was then segmented through a boolean filtering approach between the pre-and post-LULC models (Fargas et al, 2021). The boolean filtering process identified pixels classified as agricultural from the pre LULC model which were then compared to their corresponding class in the post LULC model (Fargas et al, 2021).…”

“…Their study utilized Random Forest algorithm to produce LULC maps of their agriculture-dominant area for 3 different years and agriurban conversion was then segmented through a boolean filtering approach between the pre-and post-LULC models (Fargas et al, 2021). The boolean filtering process identified pixels classified as agricultural from the pre LULC model which were then compared to their corresponding class in the post LULC model (Fargas et al, 2021). Pixels which transitioned from agriculture to either built-up or bare soil were segmented and identified as agri-urban conversion (Fargas et al, 2021).…”

“…The boolean filtering process identified pixels classified as agricultural from the pre LULC model which were then compared to their corresponding class in the post LULC model (Fargas et al, 2021). Pixels which transitioned from agriculture to either built-up or bare soil were segmented and identified as agri-urban conversion (Fargas et al, 2021).…”

“…Random Forest (RF) algorithm was used due to its flexible nature allowing it to handle non-normalized and high dimensional data (Fargas et al, 2021;Pelletier et al, 2016). Moreover, the algorithm can provide insight about variable importance which would help in better assessing the different geospatial indices used in this study.…”