Record Details

Using explainable machine learning techniques to unpack farm-level management x climate interactions

CGSpace

View Archive Info
 
 
Field Value
 
Title Using explainable machine learning techniques to unpack farm-level management x climate interactions
 
Creator Ramirez Villegas, Julian
Jaimes, Diana
Gonzalez, Carlos
Llanos, Lizeth
Jimenez, Daniel
Gardeazabal, Andrea
Estrada, Oscar
Nuñez, Daniel
 
Subject agronomic practices
adaptación al cambio climático
machine learning
adaptation
climate
agronomy
agronomía
weather
prácticas agronómicas
tiempo
estadística como ciencia
 
Description Optimizing the management of maize production systems, including the milpa (intercropping of maize with beans and other species), is crucial for improving on-farm productivity and ultimately reducing food insecurity. This presentation showcases the results of a study aimed at identifying determinants of maize yield in Guatemala using agronomic and climate data. The study employs interpretability techniques in machine learning to explain the interactions between climatic factors and crop management in productivity. The study follows a three-step approach: (1) an Extract, Transform, Load (ETL) process of data, involving feature engineering and data standardization and cleaning; (2) identification of algorithms, metrics, and algorithmic tuning; and (3) delving into interpretability using techniques such as SHAP (SHapley Additive exPlanations), partial dependence plots (PDP), accumulated local effects (ALE) plots, and Friedman's H-statistic to evaluate interactions between features
 
Date 2023-11-27
2023-12-01T10:39:40Z
2023-12-01T10:39:40Z
 
Type Presentation
 
Identifier Ramirez Villegas, J.; Jaimes, D.; Gonzalez, C.; Llanos, L.; Jimenez, D.; Gardeazabal, A.; Estrada, O.; Nuñez, D. (2023) Using explainable machine learning techniques to unpack farm-level management x climate interactions. Presentation prepared from impact to solutions, data, data science and machine learning for climate adaptation at Wageningen University & Research. 26-28 November 2023. 14 sl.
https://hdl.handle.net/10568/134910
 
Language en
 
Rights CC-BY-4.0
Open Access
 
Format 14 sl.
application/pdf