Title: Adapting CRISP-DM to model enteric fermentation emission: farm level application

Authors: Philippe Belmont Guerrón; María Hallo; Sergio Luján-Mora

Addresses: Faculty of Engineering Systems, Escuela Politecnica Nacional, Ladron de Guevara E11-253 Edif 20, Quito, Ecuador ' Faculty of Engineering Systems, Escuela Politecnica Nacional, Ladron de Guevara E11-253 Edif 20, Quito, Ecuador ' Department of Software and Computing Systems, University of Alicante, 03690 Alicante, Spain

Abstract: Enteric fermentation contributes substantially to greenhouse gas emissions (GGEs) in agriculture, but may be reversible in the short-term. To date, numerous attempts have been made to model the environmental impact of agriculture, but have failed to integrate multiple dimensions of production. The objective of this study is to adapt the cross industry standard process for data mining (CRISP-DM) at farm level, using the concept of life cycle assessment (LCA) and implemented a modified version of the global livestock environmental assessment model (GLEAM). Using local data collected over 20 years and secondary data, our results show that for dairy cattle, the methane emissions factor from cattle is lower among marginal farms 86 Kg CH₄ head^-1 year^-1 compared to semi-intensive and intensive farms across time and geographical regions (107.4 and 113.5 respectively) and demonstrate that this type of application is relevant for developing countries and smallholder agriculture, where production data is often unavailable.

Keywords: CRISP-DM; design science research; DSR; model integration; data mining; GLEAM; life cycle assessment; LCA; agriculture data; enteric fermentation.

DOI: 10.1504/IJADS.2025.145890

International Journal of Applied Decision Sciences, 2025 Vol.18 No.3, pp.330 - 359

Received: 24 Mar 2023
Accepted: 25 Dec 2023
Published online: 30 Apr 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article