Multi-step ahead soil temperature forecasting at different depths based on meteorological data: Integrating resampling algorithms and machine learning models

Direct soil temperature (ST) measurement is time-consuming and costly;thus,the use of simple and cost-effective machine learning (ML) tools is helpful.In this study,ML approaches,including KStar,instance-based K-nearest learning (IBK),and locally weighted learning (LWL),coupled with resampling algorithms of bagging (BA) and dagging (DA)(BA-IBK,BA-KStar,BA-LWL,DA-IBK,DA-KStar,and DA-LWL) were developed and tested for multi-step ahead (3,6,and 9 d ahead) ST forecasting.In addition,a linear regress...     

Evaluating the potential for farmer and plant breeder collaboration: A case study of farmer maize selection in Oaxaca, Mexico

Formal plant breeders could contribute much to collaboration with farmers for improving crop varieties for local use. To do so outside researchers must have some understanding of local selection practices and their impact on crop populations in terms of the genetic theory underlying plant breeding. In this research we integrated methods from social and biological sciences to better understand selection and its consequences from farmers' perspectives but based on the concepts used by plant breeders. Among the households we worked with, farmers' selection practices were not always effective yet they understood the reasons for this and had no expectations for response to selection in some traits given the methods available to them. Farmers' statements, practices and genetic perceptions regarding selection and the genetic response of their maize populations to their selection indicate selection objectives different than may be typically assumed, suggesting a role for plant breeder collaboration with farmers. This revised version was published online in July 2006 with corrections to the Cover Date.