Spatial downscaling of soil prediction models based on weighted generalized additive models in smallholder farm settings

Xu, Y and Smith, S E and Grunwald, S and Abd-Elrahman, A and Wani, S P and Nair, V D (2017) Spatial downscaling of soil prediction models based on weighted generalized additive models in smallholder farm settings. Environmental Monitoring and Assessment, 189 (10). pp. 1-16. ISSN 0167-6369

PDF - Published Version Restricted to ICRISAT users only Download (7MB) | Request a copy

Abstract

Digital soil mapping (DSM) is gaining momentum as a technique to help smallholder farmers secure soil security and food security in developing regions. However, communications of the digital soil mapping information between diverse audiences become problematic due to the inconsistent scale of DSM information. Spatial downscaling can make use of accessible soil information at relatively coarse spatial resolution to provide valuable soil information at relatively fine spatial resolution. The objective of this research was to disaggregate the coarse spatial resolution soil exchangeable potassium (Kex) and soil total nitrogen (TN) base map into fine spatial resolution soil downscaled map using weighted generalized additive models (GAMs) in two smallholder villages in South India. By incorporating fine spatial resolution spectral indices in the downscaling process, the soil downscaled maps not only conserve the spatial information of coarse spatial resolution soil maps but also depict the spatial details of soil properties at fine spatial resolution. The results of this study demonstrated difference between the fine spatial resolution downscaled maps and fine spatial resolution base maps is smaller than the difference between coarse spatial resolution base maps and fine spatial resolution base maps. The appropriate and economical strategy to promote the DSM technique in smallholder farms is to develop the relatively coarse spatial resolution soil prediction maps or utilize available coarse spatial resolution soil maps at the regional scale and to disaggregate these maps to the fine spatial resolution downscaled soil maps at farm scale.

Item Type:	Article
Divisions:	Research Program : Asia
CRP:	UNSPECIFIED
Uncontrolled Keywords:	Spatial downscaling, Soil nutrients, Digital soil mapping, Generalized additive models, Remote sensing, Geographic information system, Smallholder farms, Digital soil mapping, Kothapally village, GIS, Soil prediction models, Digital soil mapping information, Masuti village
Subjects:	Others > GIS Techniques/Remote Sensing Others > Soil Others > Smallholder Agriculture Others > Soil Science Others > Digital Agriculture
Depositing User:	Mr Ramesh K
Date Deposited:	25 Sep 2017 09:42
Last Modified:	30 Oct 2017 06:45
URI:	http://oar.icrisat.org/id/eprint/10191
Official URL:	http://dx.doi.org/10.1007/s10661-017-6212-z
Projects:	UNSPECIFIED
Funders:	UNSPECIFIED
Acknowledgement:	This work is supported by the grant award no. 1201943 BDevelopment of a Geospatial Soil-Crop Inference Engine for Smallholder Farmers^ EAGER National Science Foundation and Research Foundation for Youth Scholars of Beijing Technology and Business University. The soil analysis was performed in the soil laboratory at the International Crops Research Institute for the Semi-Arid Tropics (ICRISAT) in Patancheru/Hyderabad, India. We thank Christopher M. Clingensmith at the University of Florida, and ICRISAT staff members and villagers of Kothapally and Masuti for the support with field sampling. We also thank Yiming Xu’s PhD committee member Dr. Thomas K. Frazer for his commitment and guidance.A matching assistantship for Yiming Xu was provided by the School of Natural Resources and Environment, University of Florida, and China Scholarship Council.
Links:	Google Scholar

View Statistics

Actions (login required)

View Item