BOOTSTRAP AGGREGATED DECISION TREES FOR MODELING EVAPORATION PICHE USING OTHER METEOROLOGICAL FACTORS OVER ILORIN AND SOKOTO

Are, Stephen Olusegun and Alabi, Nurudeen Olawale (2018) BOOTSTRAP AGGREGATED DECISION TREES FOR MODELING EVAPORATION PICHE USING OTHER METEOROLOGICAL FACTORS OVER ILORIN AND SOKOTO. In: Commonwealth Association of Polytechnics in Africa (CAPA), 2018, Abuja, Nigeria.

Text Conference 5_Alabi NO.pdf Download (1MB)

Abstract

The threat of climate change in recent times cannot be overemphasized particularly in developing economies largely due to the connection it has with national development issues. Nigeria like most emerging economies is highly susceptible to the impact of climate change because her economy is mainly dependent on income generated from the export of crude oil. One of the main meteorological or climatic factors associated with climate change is evaporation. This current work presents models inform of decision trees to study the relationships existing between evaporation and other meteorological factors such as relative humidity, solar radiation, sunshine hours, wind speed, temperature and rainfall over the ancient cities of Sokoto and Ilorin in Nigeria. These factors are generally understood to change with rising climatic changes in a place. Analysis of the fitted trees which was done using the recursive binary splitting (RBS), cost complexity pruning, and bootstrap aggregated (boosting) reveal that relative humidity is by wide margin and varying impact, the most important meteorological factor affecting evaporation piche in both cities. Its impact is slightly more prevalent in Ilorin than Sokoto. Keywords: climate change, meteorological factors, recursive binary splitting, cost complexity pruning, boosting.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > Q Science (General)
Divisions:	Faculty of Engineering, Science and Mathematics > School of Chemistry
Depositing User:	Mr Taiwo Egbeyemi
Date Deposited:	09 Jun 2020 16:06
Last Modified:	09 Jun 2020 16:06
URI:	http://eprints.federalpolyilaro.edu.ng/id/eprint/385

Actions (login required)

View Item