Authors: Junaid Maqsood, Aitazaz A. Farooque, Farhat Abbas, Travis Esau, Xander Wang, Hassan Afzaal
Identifier: CSBE22137
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Charlottetown 2022

Download RAW file:
DOI:
Description: Precise downscaling of climatic extremes; daily maximum temperature (Tmax), minimum temperature (Tmin), and precipitation from large-scale data of general circulation models (GCMs) are valuable for making decisions regarding agriculture and water resources management. Traditionally, many statistical models have been applied to downscale the GCMs, but recent advances in machine learning have been less explored than the traditional methods. This study investigates the performance of the traditionally used statistical downscaling model and three machine learning algorithms named: random forest, support vector regression, and multilayer perceptron (MLP) in downscaling the selected climatic extremes for the baseline period (1976-2003) at eight meteorological stations across the rainfed Prince Edward Island (PEI). The comparison results revealed that MLP was the best performing algorithm among them and applied to project the climatic extremes for the future period (2006-2100) under three representative concentration pathways (RCPs), namely RCP2.6, 4.5, and 8.5. The results of the annual and seasonal, i.e., potato growing season (May-October), showed that Tmax and Tmin would continually increase in the future under all the RCPs, with the maximum increment under RCP8.5. The spatial patterns of average annual precipitation in the growing season showed high, moderate, and low precipitation at the island's eastern, central, and western parts for the baseline and future periods. This study will help the farmers to develop agricultural management practices to mitigate the impact of climate change on potato production, such as applying supplement irrigation in dry periods to fulfill the crop water requirement.

Keywords: Climate change, Machine Learning, Statistical downscaling, Linear Scaling, Agriculture
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Poster Sessions

Other information:
Type: Text.Abstract
Format:
Publication type: Poster
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files: