Mapping numerically classified soil taxa in Kilombero Valley, Tanzania using machine learning

Simple item page
dc.creatorMassawe, B. H. J.
dc.creatorSubburayalu, S. K.
dc.creatorKaaya, A. K.
dc.creatorWinowiecki, L.
dc.creatorSlater, B. K.
dc.date2019-04-16T14:15:57Z
dc.date2019-04-16T14:15:57Z
dc.date2016-11-24
dc.date.accessioned2022-10-25T08:51:48Z
dc.date.available2022-10-25T08:51:48Z
dc.descriptionGeoderma 2016; Vol 311: 143-148
dc.descriptionInadequacy of spatial soil information is one of the limiting factors to making evidence-based decisions to improve food security and land management in the developing countries. Various digital soilmapping (DSM) techniques have been applied inmany parts of theworld to improve availability and usability of soil data, but less has been done in Africa, particularly in Tanzania and at the scale necessary tomake farmmanagement decisions. The Kilombero Valley has been identified for intensified rice production. However the valley lacks detailed and up-todate soil information for decision-making. The overall objective of this study was to develop a predictive soilmap of a portion of Kilombero Valley using DSM techniques. Two widely used decision tree algorithms and three sources of Digital ElevationModels (DEMs) were evaluated for their predictive ability. Firstly, a numerical classification was performed on the collected soil profile data to arrive at soil taxa. Secondly, the derived taxawere spatially predicted and mapped following SCORPAN framework using Random Forest (RF) and J48 machine learning algorithms. Datasets to train the model were derived from legacy soil map, RapidEye satellite image and three DEMs: 1 arc SRTM, 30 m ASTER, and 12 m WorldDEM. Separate predictive models were built using each DEM source. Mapping showed that RF was less sensitive to the training set sampling intensity. Results also showed that predictions of soil taxa using 1 arc SRTM and 12mWordDEMwere identical.We suggest the use of RF algorithmand the freely available SRTMDEMcombination formapping the soils for thewhole Kilombero Valley. This combination can be tested and applied in other areas which have relatively flat terrain like the Kilombero Valley
dc.formatapplication/pdf
dc.identifierhttps://www.suaire.sua.ac.tz/handle/123456789/2774
dc.identifier.urihttp://hdl.handle.net/123456789/91766
dc.languageen
dc.publisherElsevier
dc.subjectKilombero Valley
dc.subjectNumerical classification
dc.subjectMachine learning
dc.subjectSoil mapping
dc.subjectDecision tree analysis
dc.subjectDEM
dc.titleMapping numerically classified soil taxa in Kilombero Valley, Tanzania using machine learning
dc.typeArticle

Files

Collections

Sokoine University