Mapping Prominent Cash Crops Employing ALOS PALSAR-2 and Selected Machine Learners

Panuju, Dyah R. and Haerani, H. and Apan, Armando ORCID: https://orcid.org/0000-0002-5412-8881 and Griffin, Amy L. and Paull, David J. and Trisasongko, Bambang Hendro (2022) Mapping Prominent Cash Crops Employing ALOS PALSAR-2 and Selected Machine Learners. In: Agriculture, Livestock Production and Aquaculture: Advances for Smallholder Farming Systems. Springer, Cham, Switzerland, pp. 131-146. ISBN 9783030932619


Abstract

Monitoring crops area is essential in achieving food security. The production coverage, crop types, and their growth phases are the key for monitoring food supply. Remote sensing plays a critical role to provide reliable data on regional basis supporting food production monitoring. In this research, we evaluated the use of Phased Array-type L-band Synthetic Aperture Radar (PALSAR-2), coupling with selected machine learners to map crop areas in the South Burnett, Queensland, Australia. Feature amendments onto dual polarimetric of ALOS PALSAR-2 were then assessed by means of variable importance to improve classification performance. Four machine learners were selected based on previous research and evaluated through classification accuracy. The best performer was Random Forest followed by C5.0, which generated accuracy at 82% and 81%, respectively. The response of data amendment varied over different classifiers. Random Forest and C5.0 seem to produce the highest accuracy at the best data-subset, while additional features with contribution less than 20% tended to reduce the accuracies of the two classifiers. Meanwhile, extreme gradient boosting tree and support vector machine kept increasing their accuracies, although additional features contributed trivially.


Statistics for USQ ePrint 49987
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Additional Information: Files associated with this item cannot be displayed due to copyright restrictions.
Faculty/School / Institute/Centre: Current – Faculty of Health, Engineering and Sciences - School of Surveying and Built Environment (1 Jan 2022 -)
Faculty/School / Institute/Centre: Current – Faculty of Health, Engineering and Sciences - School of Surveying and Built Environment (1 Jan 2022 -)
Date Deposited: 20 Jul 2022 22:59
Last Modified: 19 Oct 2022 01:57
Uncontrolled Keywords: C5, crops mapping, Extreme gradient boosting tree, PALSAR-2, Polarimetry, Random forest, Support vector machine
Fields of Research (2020): 40 ENGINEERING > 4013 Geomatic engineering > 401304 Photogrammetry and remote sensing
40 ENGINEERING > 4013 Geomatic engineering > 401302 Geospatial information systems and geospatial data modelling
30 AGRICULTURAL, VETERINARY AND FOOD SCIENCES > 3004 Crop and pasture production > 300405 Crop and pasture biomass and bioproducts
Socio-Economic Objectives (2020): 26 PLANT PRODUCTION AND PLANT PRIMARY PRODUCTS > 2603 Grains and seeds > 260303 Grain legumes
Identification Number or DOI: https://doi.org/10.1007/978-3-030-93262-6_9
URI: http://eprints.usq.edu.au/id/eprint/49987

Actions (login required)

View Item Archive Repository Staff Only