Mapping of soil properties and land degradation risk in Africa using MODIS reflectance

Vågen, Tor-Gunnar; Winowiecki, Leigh A.; Tondoh, Jérôme E.; Desta, L.; Gumbricht, Thomas

doi:10.1016/j.geoderma.2015.06.023

Cited by 164 publications

(130 citation statements)

References 37 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…60 sites of 10 by 10 km (Walsh and Vågen 2006;Vågen et al 2010). Samples were taken in the period 2008-2016 at 0-20 and 20-50 cm soil depth intervals; analyzed by mid-infrared (MIR) diffuse reflectance spectroscopy based on calibration points from 960 samples (10%) analyzed by conventional wet chemistry including Mehlich-3, and thermal oxidation for org.…”

Section: Soil Nutrient Samplesmentioning

confidence: 99%

“…Large gaps in geographical coverage also often occur due to limitations on sampling such as accessibility and safety issues, so that especially tropical forests and wetlands are under-represented in the sampling designs. Nevertheless, in most of main sampling campaigns such as the AfSIS sentinel sites, locations were purposely selected to represent the main climatic zones (Vågen et al 2010), so in this sense coverage of sampling locations can be considered satisfactory for most nutrients.…”

Section: Soil Nutrient Samplesmentioning

confidence: 99%

“…Detailed maps of soil nutrients, including micronutrients, are now possible due to the increasing inflow of soil samples collected at field point locations by various government and/or NGO funded projects: e.g. by projects supported by the National Governments of Ethiopia, Tanzania, Kenya, Uganda, Nigeria, Ghana, Rwanda, Burundi and others; and by organizations such as the Bill and Melinda Gates Foundation (Leenaars 2012;Shepherd et al 2015;Towett et al 2015;Vågen et al 2016) and similar, as well as by the private sector.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning

Hengl

Leenaars

Shepherd

et al. 2017

Nutr Cycl Agroecosyst

221

148

View full text Add to dashboard Cite

Spatial predictions of soil macro and micro-nutrient content across Sub-Saharan Africa at 250 m spatial resolution and for 0-30 cm depth interval are presented. Predictions were produced for 15 target nutrients: organic carbon (C) and total (organic) nitrogen (N), total phosphorus (P), and extractable-phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), manganese (Mn), zinc (Zn), copper (Cu), aluminum (Al) and boron (B). Model training was performed using soil samples from ca. 59,000 locations (a compilation of soil samples from the AfSIS, EthioSIS, One Acre Fund, VitalSigns and legacy soil data) and an extensive stack of remote sensing covariates in addition to landform, lithologic and land cover maps. An ensemble model was then created for each nutrient from two machine learning algorithms- random forest and gradient boosting, as implemented in R packages ranger and xgboost-and then used to generate predictions in a fully-optimized computing system. Cross-validation revealed that apart from S, P and B, significant models can be produced for most targeted nutrients (R-square between 40-85%). Further comparison with OFRA field trial database shows that soil nutrients are indeed critical for agricultural development, with Mn, Zn, Al, B and Na, appearing as the most important nutrients for predicting crop yield. A limiting factor for mapping nutrients using the existing point data in Africa appears to be (1) the high spatial clustering of sampling locations, and (2) missing more detailed parent material/geological maps. Logical steps towards improving prediction accuracies include: further collection of input (training) point samples, further harmonization of measurement methods, addition of more detailed covariates specific to Africa, and implementation of a full spatiotemporal statistical modeling framework.

show abstract

Section: Soil Nutrient Samplesmentioning

confidence: 99%

Section: Soil Nutrient Samplesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning

Hengl

Leenaars

Shepherd

et al. 2017

Nutr Cycl Agroecosyst

221

148

View full text Add to dashboard Cite

show abstract

“…We applied the Land Degradation Surveillance Framework (LDSF) (Vågen et al 2010(Vågen et al , 2013bVågen and Gumbritch 2012) in order to assess land and soil health in the study area. The LDSF is a spatially stratified hierarchical sampling design aimed at assessing key land and soil health metrics across diverse landscapes (Fig.…”

Section: Soil and Land Health Surveymentioning

confidence: 99%

“…The measured wavebands ranged from 4000 to 601 cm -1 with a resolution of 4 cm -1 . Soil samples that have both MIR spectra and associated wet chemistry data were used to develop the MIR prediction models for the various soil properties (Vågen et al 2016). Processing of the MIR spectra followed the procedures outlined in Terhoeven- Urselmans et al (2010), with first derivatives computed using a Savitsky-Golay polynomial smoothing filter implemented in the locpoly function of the KernSmooth R package (Wand 2015) prior to fitting a random forest (RF) prediction model to the samples from the study area.…”

Section: Soil Laboratory Analysismentioning

confidence: 99%

Landscape-scale variability of soil health indicators: effects of cultivation on soil organic carbon in the Usambara Mountains of Tanzania

Winowiecki

Vågen

Massawe

et al. 2015

Nutr Cycl Agroecosyst

View full text Add to dashboard Cite

Land-use change continues at an alarming rate in sub-Saharan Africa adversely affecting ecosystem services provided by soil. These impacts are greatly understudied, especially in biodiversity rich mountains in East Africa. The objectives of this study were to: conduct a biophysical baseline of soil and land health; assess the effects of cultivation on soil organic carbon (SOC); and develop a map of SOC at high resolution to enable farm-scale targeting of management interventions. Biophysical field surveys were conducted in a 100 km 2 landscape near Lushoto, Tanzania, with composite soil samples collected from 160 sampling plots. Soil erosion prevalence was scored, trees were counted, and current and historic land use was recorded at each plot. The results of the study showed a decline in SOC as a result of cultivation, with cultivated plots (n = 105) having mean topsoil OC of 30.6 g kg -1 , while semi-natural plots (n = 55) had 71 g OC kg -1 in topsoil. Cultivated areas were also less variable in SOC than seminatural systems. Prediction models were developed for the mapping of SOC based on RapidEye remote sensing data for January 2014, with good model performance (RMSEP cal = 8.0 g kg -1 ; RMSEP val = 10.5 g kg -1 ) and a SOC map was generated for the study. Interventions will need to focus on practices that increase SOC in order to enhance productivity and resilience of the farming system, in general. The highresolution maps can be used to spatially target interventions as well as for monitoring of changes in SOC.

show abstract

Current Trends and Future Scope for the Internet of Things

Abrar

Ayub

Masoodi

2021

Internet of Things in Business Transformation

View full text Add to dashboard Cite

Mapping of soil properties and land degradation risk in Africa using MODIS reflectance

Cited by 164 publications

References 37 publications

Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning

Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning

Landscape-scale variability of soil health indicators: effects of cultivation on soil organic carbon in the Usambara Mountains of Tanzania

Current Trends and Future Scope for the Internet of Things

Contact Info

Product

Resources

About