Journal metrics

Journal metrics

  • IF value: 3.769 IF 3.769
  • IF 5-year value: 4.522 IF 5-year 4.522
  • CiteScore value: 4.14 CiteScore 4.14
  • SNIP value: 1.170 SNIP 1.170
  • SJR value: 2.253 SJR 2.253
  • IPP value: 3.86 IPP 3.86
  • h5-index value: 26 h5-index 26
  • Scimago H index value: 22 Scimago H index 22
Volume 8, issue 1 | Copyright
Earth Syst. Dynam., 8, 55-73, 2017
https://doi.org/10.5194/esd-8-55-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.

Research article 08 Feb 2017

Research article | 08 Feb 2017

Continuous and consistent land use/cover change estimates using socio-ecological data

Michael Marshall1, Michael Norton-Griffiths1, Harvey Herr1, Richard Lamprey2, Justin Sheffield3, Tor Vagen1, and Joseph Okotto-Okotto4 Michael Marshall et al.
  • 1Climate Research Unit, World Agroforestry Centre, United Nations Ave, Gigiri, P.O. Box 30677-00100, Nairobi, Kenya
  • 2Fauna & Flora International, The David Attenborough Building, Pembroke St, Cambridge, CB2 3QZ, UK
  • 3Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ 08544, USA
  • 4Lake Basin Development Authority, P.O. Box 1516-40100, Kisumu, Kenya

Abstract. A growing body of research shows the importance of land use/cover change (LULCC) on modifying the Earth system. Land surface models are used to stimulate land–atmosphere dynamics at the macroscale, but model bias and uncertainty remain that need to be addressed before the importance of LULCC is fully realized. In this study, we propose a method of improving LULCC estimates for land surface modeling exercises. The method is driven by projectable socio-ecological geospatial predictors available seamlessly across sub-Saharan Africa and yielded continuous (annual) estimates of LULCC at 5km × 5km spatial resolution. The method was developed with 2252 sample area frames of 5km × 5km consisting of the proportion of several land cover types in Kenya over multiple years. Forty-three socio-ecological predictors were evaluated for model development. Machine learning was used for data reduction, and simple (functional) relationships defined by generalized additive models were constructed on a subset of the highest-ranked predictors (p ≤ 10) to estimate LULCC. The predictors explained 62 and 65% of the variance in the proportion of agriculture and natural vegetation, respectively, but were less successful at estimating more descriptive land cover types. In each case, population density on an annual basis was the highest-ranked predictor. The approach was compared to a commonly used remote sensing classification procedure, given the wide use of such techniques for macroscale LULCC detection, and outperformed it for each land cover type. The approach was used to demonstrate significant trends in expanding (declining) agricultural (natural vegetation) land cover in Kenya from 1983 to 2012, with the largest increases (declines) occurring in densely populated high agricultural production zones. Future work should address the improvement (development) of existing (new) geospatial predictors and issues of model scalability and transferability.

Download & links
Publications Copernicus
Download
Short summary
The transition of land from one cover type to another can adversely affect the Earth system. A growing body of research aims to map these transitions in space and time to better understand the impacts. Here we develop a statistical model that is parameterized by socio-ecological geospatial data and extensive aerial/ground surveys to visualize and interpret these transitions on an annual basis for 30 years in Kenya. Future work will use this method to project land suitability across Africa.
The transition of land from one cover type to another can adversely affect the Earth system. A...
Citation
Share