Creating Low-Cost Soil Maps for Tropical Agriculture using Gaussian Processes

Juan Pablo Gonzalez, Simon Cook, Thomas Oberthur, Andrew Jarvis, J. Andrew (Drew) Bagnell, and M Bernardine Dias
Workshop on AI in ICT for Development (ICTD) at the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 2007), January, 2007.


Download
  • Adobe portable document format (pdf) (856KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Soil maps are essential resources to soil scientists and researchers in any fields related to soil, land use, species conservation, hunger reduction, social development, etc. However, creating detailed soil maps is an expensive and time consuming task that most developing nations cannot afford. In recent years, there has been a significant shift towards digital representation of soil maps and environmental variables that has created the field of predictive soil mapping (PSM), where statistical analysis is used to create predictive models of soil properties. PSM requires less human intervention than traditional soil mapping techniques, and relies more on computers to create models and predict properties. However, because most of the funds for soil research come from developed nations, the research in this field has mostly focused in temperate zones where these nations are located. The areas of the world with more needs in terms of hunger and poverty are mostly located in the tropics, and require different statistical models because of the unique characteristics of their weather and environment. This paper reports on collaborative work with a group of soil scientists from the International Center for Tropical Agriculture (CIAT) and a group of computer scientists from Carnegie Mellon University to develop statistical soil models for Honduras. The reported work leverages the knowledge of the soil science and computer science communities, and creates a model that contributes to the state of the art for PSM.

Keywords
Predictive Soil Mapping, Gaussian Processes, Tropical Agriculture

Notes
Associated Center(s) / Consortia: Field Robotics Center
Number of pages: 6
Note: TechBridgeWorld

Text Reference
Juan Pablo Gonzalez, Simon Cook, Thomas Oberthur, Andrew Jarvis, J. Andrew (Drew) Bagnell, and M Bernardine Dias, "Creating Low-Cost Soil Maps for Tropical Agriculture using Gaussian Processes," Workshop on AI in ICT for Development (ICTD) at the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 2007), January, 2007.

BibTeX Reference
@inproceedings{Gonzalez_2007_5747,
   author = "Juan Pablo Gonzalez and Simon Cook and Thomas Oberthur and Andrew Jarvis and J. Andrew (Drew) Bagnell and M Bernardine Dias",
   title = "Creating Low-Cost Soil Maps for Tropical Agriculture using Gaussian Processes",
   booktitle = "Workshop on AI in ICT for Development (ICTD) at the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 2007)",
   month = "January",
   year = "2007",
   Notes = "TechBridgeWorld"
}