scholarly journals African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tomislav Hengl ◽  
Matthew A. E. Miller ◽  
Josip Križan ◽  
Keith D. Shepherd ◽  
Andrew Sila ◽  
...  

AbstractSoil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mapped at all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGO funded projects, it is now possible to produce detailed pan-African maps of soil nutrients, including micro-nutrients at fine spatial resolutions. In this paper we describe production of a 30 m resolution Soil Information System of the African continent using, to date, the most comprehensive compilation of soil samples ($$N \approx 150,000$$ N ≈ 150 , 000 ) and Earth Observation data. We produced predictions for soil pH, organic carbon (C) and total nitrogen (N), total carbon, effective Cation Exchange Capacity (eCEC), extractable—phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), zinc (Zn)—silt, clay and sand, stone content, bulk density and depth to bedrock, at three depths (0, 20 and 50 cm) and using 2-scale 3D Ensemble Machine Learning framework implemented in the (Machine Learning in ) package. As covariate layers we used 250 m resolution (MODIS, PROBA-V and SM2RAIN products), and 30 m resolution (Sentinel-2, Landsat and DTM derivatives) images. Our fivefold spatial Cross-Validation results showed varying accuracy levels ranging from the best performing soil pH (CCC = 0.900) to more poorly predictable extractable phosphorus (CCC = 0.654) and sulphur (CCC = 0.708) and depth to bedrock. Sentinel-2 bands SWIR (B11, B12), NIR (B09, B8A), Landsat SWIR bands, and vertical depth derived from 30 m resolution DTM, were the overall most important 30 m resolution covariates. Climatic data images—SM2RAIN, bioclimatic variables and MODIS Land Surface Temperature—however, remained as the overall most important variables for predicting soil chemical variables at continental scale. This publicly available 30-m Soil Information System of Africa aims at supporting numerous applications, including soil and fertilizer policies and investments, agronomic advice to close yield gaps, environmental programs, or targeting of nutrition interventions.

2020 ◽  
Author(s):  
Tomislav Hengl ◽  
Matthew Miller ◽  
Josip Krizan ◽  
Keith Shepherd ◽  
Andrew Sila ◽  
...  

Abstract Soil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mappedat all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGOfunded projects, it is now possible to produce detailed pan-African maps of soil nutrients, including micro-nutrients at fine spatial resolutions. Inthis paper we describe production of a 30 m resolution Soil Information System of the African continent using, to date, the most comprehensivecompilation of soil samples (N ≈ 150, 000) and Earth Observation data. We produced predictions for soil pH, organic carbon (C) and totalnitrogen (N), total carbon, Cation Exchange Capacity (eCEC), extractable — phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg),sulfur (S), sodium (Na), iron (Fe), zinc (Zn) — silt, clay and sand, stone content, bulk density and depth to bedrock, at three depths (0, 20 and50 cm) and using 2-scale 3D Ensemble Machine Learning framework implemented in the mlr (Machine Learning in R) package. As covariatelayers we used 250 m resolution (MODIS, PROBA-V and SM2RAIN products), and 30 m resolution (Sentinel-2, Landsat and DTM derivatives)images. Our 5–fold spatial Cross-Validation results showed varying accuracy levels ranging from the best performing soil pH (CCC=0.900) tomore poorly predictable extractable phosphorus (CCC=0.654) and sulphur (CCC=0.708) and depth to bedrock. Sentinel-2 bands SWIR (B11,B12), NIR (B09, B8A), Landsat SWIR bands, and vertical depth derived from 30 m resolution DTM, were the overall most important 30 mresolution covariates. Climatic data images — SM2RAIN, bioclimatic variables and MODIS Land Surface Temperature — however, remainedas the overall most important variables for predicting soil chemical variables at continental scale. The publicly available 30–m soil maps aresuitable for numerous applications, including soil and fertilizer policies and investments, agronomic advice to close yield gaps, environmentalprograms, or targeting of nutrition interventions.


2020 ◽  
Vol 12 (3) ◽  
pp. 355 ◽  
Author(s):  
Nam Thang Ha ◽  
Merilyn Manley-Harris ◽  
Tien Dat Pham ◽  
Ian Hawes

Seagrass has been acknowledged as a productive blue carbon ecosystem that is in significant decline across much of the world. A first step toward conservation is the mapping and monitoring of extant seagrass meadows. Several methods are currently in use, but mapping the resource from satellite images using machine learning is not widely applied, despite its successful use in various comparable applications. This research aimed to develop a novel approach for seagrass monitoring using state-of-the-art machine learning with data from Sentinel–2 imagery. We used Tauranga Harbor, New Zealand as a validation site for which extensive ground truth data are available to compare ensemble machine learning methods involving random forests (RF), rotation forests (RoF), and canonical correlation forests (CCF) with the more traditional maximum likelihood classifier (MLC) technique. Using a group of validation metrics including F1, precision, recall, accuracy, and the McNemar test, our results indicated that machine learning techniques outperformed the MLC with RoF as the best performer (F1 scores ranging from 0.75–0.91 for sparse and dense seagrass meadows, respectively). Our study is the first comparison of various ensemble-based methods for seagrass mapping of which we are aware, and promises to be an effective approach to enhance the accuracy of seagrass monitoring.


2021 ◽  
Author(s):  
Diarmuid Corr ◽  
Amber Leeson ◽  
Malcolm McMillan ◽  
Ce Zhang

<p>Mass loss from Greenlandic and Antarctic ice sheets are predicted to be the dominant contribution to global sea level rise in coming years. Supraglacial lakes and channels are thought to play a significant role in ice sheet mass balance by causing the speed-up of grounded ice and weakening, floating ice shelves to the point of collapse. Identifying the location, distribution and life cycle of these hydrological features on both the Greenland and Antarctic ice sheets is therefore important in understanding their present and future contribution to global sea level rise. Supraglacial hydrological features can be easily identified by eye in optical satellite imagery. However, given that there are many thousands of these features, and they appear in many hundreds of satellite images, automated approaches to mapping these features in such images are urgently needed.</p><p> </p><p>Current automated approaches in mapping supraglacial hydrology tend to have high false positive and false negative rates, which are often followed by manual corrections and quality control processes. Given the scale of the data however, methods such as those that require manual post-processing are not feasible for repeat monitoring of surface hydrology at continental scale. Here, we present initial results from our work conducted as part of the 4D Greenland and 4D Antarctica projects, which increases the accuracy of supraglacial lake and channel delineation using Sentinel-2 and Landsat-7/8 imagery, while reducing the need for manual intervention. We use Machine Learning approaches including a Random Forest algorithm trained to recognise water, ice, cloud, rock, shadow, blue-ice and crevassed regions. Both labelled optical imagery and auxiliary data (e.g. digital elevation models) are used in our approach. Our methods are trained and validated using data covering a range of glaciological and climatological conditions, including images of both ice sheets and those acquired at different points during the melt-season. The workflow, developed under Google Cloud Platform, which hosts the entire archive of Sentinel-2 and Landsat-8 data, allows for large-scale application over Greenlandic and Antarctic ice sheets, and is intended for repeated use throughout future melt-seasons.</p>


1986 ◽  
Vol 16 (4) ◽  
pp. 689-695 ◽  
Author(s):  
Mary E. Watwood ◽  
John W. Fitzgerald ◽  
James R. Gosz

O2 litter and A1 horizon soil samples from various locations within the Santa Fe and Cibola National Forests of New Mexico were assayed for sulfate adsorption, organic S formation, and organic S solubilization and mineralization (mobilization). During a 48-h incubation, samples of O2 litter were found to adsorb between 1.6 and 4.1 nmol g−1 of added sulfate S and to form 2.0 to 9.8 nmol g−1 of organic S from this anion. Between 17 and 48% of this organic S was mobilized within 24 h. A1 horizon soils adsorbed 1.2 to 4.9 nmol g−1 of added sulfate S and formed between 1.6 and 4.8 nmol g−1 of organic S during 48 h. Between 20 and 50% of this organic S was mobilized within 24 h. Estimations of S-accumulation potentials for both horizons were made from these determinations. Intrinsic S pools were quantified to determine the S status of the samples prior to incubation. Carbon-bonded forms of S were found to predominate in samples from both horizons, while ester sulfate accounted for most of the remaining S. Sample pH, moisture content, and total carbon content were also determined. Attempts were made to correlate these characteristics and S pool sizes with laboratory determined potentials for sulfate adsorption, organic S formation, and mobilization. For some sites, relationships were established between sulfate adsorption, soil pH, and total C, whereas the total S and organic S content of most samples agreed well with organic S formation potentials.


1974 ◽  
Vol 54 (4) ◽  
pp. 379-385 ◽  
Author(s):  
T. G. ALEXANDER ◽  
J. A. ROBERTSON

Soil samples from virgin profiles of Solonetzic and geographically associated Chernozemic series along with Ap horizons of Solonetzic and Chernozemic soils were taken. Soil pH, organic C, oxalate-extractable Al and Fe, inorganic P forms, organic and total P, and extractable P by NH4F + H3SO4 and NaHCO3 methods were determined. On the average, Solonetzic sola had higher contents of oxalate-extractable Al and Fe, Fe-P, and lower levels of Ca-P than do their associated Chernozemic sola. There was not a clear difference in Al-P contents between the sola of the two Orders. Ap samples from Solonetzic soils had twice the amount of NH4F + H2SO4- and NaHCO3-extractable P found in the Chernozemic ones. The higher levels of extractable P in the Solonetzic than in the Chernozemic Ap samples could be explained by the higher contents of Al-P and Fe-P in the former. The high acidity in the upper sola of Solonetzic soils, indicative of intense weathering conditions, apparently has resulted in relatively high contents of oxalate-extractable Al and Fe, and these probably account for the higher levels of Al-P and Fe-P and lower levels of Ca-P in the Solonetzic than in the Chernozemic soils.


2021 ◽  
Vol 13 (8) ◽  
pp. 1494
Author(s):  
James M. Muthoka ◽  
Edward E. Salakpi ◽  
Edward Ouko ◽  
Zhuang-Fang Yi ◽  
Alexander S. Antonarakis ◽  
...  

Globally, grassland biomes form one of the largest terrestrial covers and present critical social–ecological benefits. In Kenya, Arid and Semi-arid Lands (ASAL) occupy 80% of the landscape and are critical for the livelihoods of millions of pastoralists. However, they have been invaded by Invasive Plant Species (IPS) thereby compromising their ecosystem functionality. Opuntia stricta, a well-known IPS, has invaded the ASAL in Kenya and poses a threat to pastoralism, leading to livestock mortality and land degradation. Thus, identification and detailed estimation of its cover is essential for drawing an effective management strategy. The study aimed at utilizing the Sentinel-2 multispectral sensor to detect Opuntia stricta in a heterogeneous ASAL in Laikipia County, using ensemble machine learning classifiers. To illustrate the potential of Sentinel-2, the detection of Opuntia stricta was based on only the spectral bands as well as in combination with vegetation and topographic indices using Extreme Gradient Boost (XGBoost) and Random Forest (RF) classifiers to detect the abundance. Study results showed that the overall accuracies of Sentinel 2 spectral bands were 80% and 84.4%, while that of combined spectral bands, vegetation, and topographic indices was 89.2% and 92.4% for XGBoost and RF classifiers, respectively. The inclusion of topographic indices that enhance characterization of biological processes, and vegetation indices that minimize the influence of soil and the effects of atmosphere, contributed by improving the accuracy of the classification. Qualitatively, Opuntia stricta spatially was found along river banks, flood plains, and near settlements but limited in forested areas. Our results demonstrated the potential of Sentinel-2 multispectral sensors to effectively detect and map Opuntia stricta in a complex heterogeneous ASAL, which can support conservation and rangeland management policies that aim to map and list threatened areas, and conserve the biodiversity and productivity of rangeland ecosystems.


2020 ◽  
Author(s):  
James Muthoka ◽  
Pedram Rowhani ◽  
Alexander Antonarakis

<p>To ensure effective management of Alien plant species especially the invasive demands for knowledge of their spatial availability. The use of satellite remote sensing tools has increasingly provided potential ways to assess spatial availability as compared to the traditional ways that are inadequate to provide similar information in a detailed way. The Copernicus Sentinel satellite images with a high spatial resolution and easy access at no charge provides an opportunity for mapping the spatial variability at a regional scale and in a detailed manner. In this study, we assess the potential of Sentinel 2 images vegetation indices and using ensemble machine learning techniques, map the spatial variability of invasive species (Opuntia stricta) in an arid and semi-arid region of Kenya. To actualize this, we use Sentinel 2 bands and thirty-one vegetation and elevation indices for classification. Field data collected is divided into two (training & validation) and used to get the best model to classify Opuntia stricta and eight other control classes. The best performing model and the highest contributing features are selected for final Opuntia stricta estimation. The random forest algorithm yields the highest accuracy 89% hence is used to classify Opuntia stricta species. Our observation of the overall results indicates that Sentinels in combination with the indices characterized by spatial resolution provide an importance that can be used to discriminate Opuntia stricta species hence providing an opportunity for long term monitoring and management at a fairly acceptable accuracy hence ensuring limited pasture degradation. Therefore, future research should focus on exploring Sentinel time-series images for estimating Opuntia stricta species at a temporal variability.</p>


2020 ◽  
Vol 5 (1) ◽  
pp. 13
Author(s):  
Negar Tavasoli ◽  
Hossein Arefi

Assessment of forest above ground biomass (AGB) is critical for managing forest and understanding the role of forest as source of carbon fluxes. Recently, satellite remote sensing products offer the chance to map forest biomass and carbon stock. The present study focuses on comparing the potential use of combination of ALOSPALSAR and Sentinel-1 SAR data, with Sentinel-2 optical data to estimate above ground biomass and carbon stock using Genetic-Random forest machine learning (GA-RF) algorithm. Polarimetric decompositions, texture characteristics and backscatter coefficients of ALOSPALSAR and Sentinel-1, and vegetation indices, tasseled cap, texture parameters and principal component analysis (PCA) of Sentinel-2 based on measured AGB samples were used to estimate biomass. The overall coefficient (R2) of AGB modelling using combination of ALOSPALSAR and Sentinel-1 data, and Sentinel-2 data were respectively 0.70 and 0.62. The result showed that Combining ALOSPALSAR and Sentinel-1 data to predict AGB by using GA-RF model performed better than Sentinel-2 data.


Sign in / Sign up

Export Citation Format

Share Document