No abstract

The mapping of soil attributes provides support to agricultural planning and land use monitoring, which consequently aids the improvement of soil quality and food production. Landsat 5 Thematic Mapper (TM) images are often used to estimate a given soil attribute (i.e., clay), but have the potential to model many other attributes, providing input for soil mapping applications. In this paper, we aim to evaluate a Bare Soil Composite Image (BSCI) from the state of São Paulo, Brazil, calculated from a multi-temporal dataset, and study its relationship with topsoil properties, such as soil class and geology. The method presented detects bare soil in satellite images in a time series of 16 years, based on Landsat 5 TM observations. The compilation derived a BSCI for the agricultural sites (242,000 hectare area) characterized by very complex geology. Soil properties were analyzed to calibrate prediction models using 740 soil samples (0–20 cm) collected of the area. Partial least squares regression (PLSR) based on the BSCI spectral dataset was performed to quantify soil attributes. The method identified that a single image represents 7 to 20% of bare soil while the compilation of the multi-temporal dataset increases to 53%. Clay content had the best soil attribute prediction estimates (R2 = 0.75, root mean square error (RMSE) = 89.84 g kg−1, and accuracy = 74%). Soil organic matter, cation exchange capacity and sandy soils also achieved moderate predictions. The BSCI demonstrates a strong relationship with legacy geological maps detecting variations in soils. From a single composite image, it was possible to use spectroscopy to evaluate several environmental parameters. This technique could greatly improve soil mapping and consequently aid several applications, such as land use planning, environmental monitoring, and prevention of land degradation, updating legacy surveys and digital soil mapping.

Soil mapping demands large-scale surveys that are costly and time consuming. It is necessary to identify strategies with reduced costs to obtain detailed information for soil mapping. We aimed to compare multispectral satellite image and relief parameters for the quantification and mapping of clay and sand contents. The Temporal Synthetic Spectral (TESS) reflectance and Synthetic Soil Image (SYSI) approaches were used to identify and characterize texture spectral signatures at the image level. Soil samples were collected (0–20 cm depth, 919 points) from an area of 14,614 km2 in Brazil for reference and model calibration. We compared different prediction approaches: (a) TESS and SYSI; (b) Relief-Derived Covariates (RDC); and (c) SYSI plus RDC. The TESS method produced highly similar behavior to the laboratory convolved data. The sandy textural class showed a greater increase in average spectral reflectance from Band 1 to 7 compared with the clayey class. The prediction using SYSI produced a better result for clay (R2 = 0.83; RMSE = 65.0 g kg−1) and sand (R2 = 0.86; RMSE = 79.9 g kg−1). Multispectral satellite images were more stable for the identification of soil properties than relief parameters.

the earth's surface dynamics provide essential information for guiding environmental and agricultural policies. Uncovered and unprotected surfaces experience several undesirable effects, which can affect soil ecosystem functions. We developed a technique to identify global bare surface areas and their dynamics based on multitemporal remote sensing images to aid the spatiotemporal evaluation of anthropic and natural phenomena. The bare Earth's surface and its changes were recognized by Landsat image processing over a time range of 30 years using the Google Earth Engine platform. Two additional products were obtained with a similar technique: a) Earth's bare surface frequency, which represents where and how many times a single pixel was detected as bare surface, based on Landsat series, and b) Earth's bare soil tendency, which represents the tendency of bare surface to increase or decrease. This technique enabled the retrieval of bare surfaces on 32% of Earth's total land area and on 95% of land when considering only agricultural areas. From a multitemporal perspective, the technique found a 2.8% increase in bare surfaces during the period on a global scale. However, the rate of soil exposure decreased by ~4.8% in the same period. The increase in bare surfaces shows that agricultural areas are increasing worldwide. The decreasing rate of soil exposure indicates that, unlike popular opinion, more soils have been covered due to the adoption of conservation agriculture practices, which may reduce soil degradation. Soils are directly related to global issues, such as food supply, water security and climate regulation 1-4. Considering that soil health is easily disturbed by modifications of physical, chemical and biological conditions, soil management must be carefully delineated and constantly monitored 5. The high occurrence of bare surfaces in agricultural areas may increase soil degradation, influencing soil health and affecting important ecosystem functions 6. Surface exposure triggers a sequence of events, which may result in soil erosion 7 , contamination 8 , desertification 9 , salinization 10 , acidification 11 , compaction 12 , biodiversity loss 13 , nutrient depletion 14 , and loss of soil organic carbon (SOC) 15. Despite the need to preserve soil ecosystems for future generations, we will still need to feed 9.7 billion people by the middle of this century 16. To date, the total area of worldwide crop and pasture lands is estimated at 49 million km 2 , which represents approximately 30% of the total global land area 17. The world's future demand for water, energy and food is closely related to the intensification of agriculture and the preservation of ecosystems. Sustainable land use requires data-driven policymaking and management strategies, which are currently hampered by the high cost and time-consuming characteristics of soil data acquisition 2. The remote sensing (RS) technique is an indispensable tool for multitemporal and spatial data acquisition, as it enables the collection of soil information at gl...

Abstract. The number of samples used in the calibration data set affects the quality of the generated predictive models using visible, near and shortwave infrared (VIS–NIR–SWIR) spectroscopy for soil attributes. Recently, the convolutional neural network (CNN) has been regarded as a highly accurate model for predicting soil properties on a large database. However, it has not yet been ascertained how large the sample size should be for CNN model to be effective. This paper investigates the effect of the training sample size on the accuracy of deep learning and machine learning models. It aims at providing an estimate of how many calibration samples are needed to improve the model performance of soil properties predictions with CNN as compared to conventional machine learning models. In addition, this paper also looks at a way to interpret the CNN models, which are commonly labelled as a black box. It is hypothesised that the performance of machine learning models will increase with an increasing number of training samples, but it will plateau when it reaches a certain number, while the performance of CNN will keep improving. The performances of two machine learning models (partial least squares regression – PLSR; Cubist) are compared against the CNN model. A VIS–NIR–SWIR spectra library from Brazil, containing 4251 unique sites with averages of two to three samples per depth (a total of 12 044 samples), was divided into calibration (3188 sites) and validation (1063 sites) sets. A subset of the calibration data set was then created to represent a smaller calibration data set ranging from 125, 300, 500, 1000, 1500, 2000, 2500 and 2700 unique sites, which is equivalent to a sample size of approximately 350, 840, 1400, 2800, 4200, 5600, 7000 and 7650. All three models (PLSR, Cubist and CNN) were generated for each sample size of the unique sites for the prediction of five different soil properties, i.e. cation exchange capacity, organic carbon, sand, silt and clay content. These calibration subset sampling processes and modelling were repeated 10 times to provide a better representation of the model performances. Learning curves showed that the accuracy increased with an increasing number of training samples. At a lower number of samples (< 1000), PLSR and Cubist performed better than CNN. The performance of CNN outweighed the PLSR and Cubist model at a sample size of 1500 and 1800, respectively. It can be recommended that deep learning is most efficient for spectra modelling for sample sizes above 2000. The accuracy of the PLSR and Cubist model seems to reach a plateau above sample sizes of 4200 and 5000, respectively, while the accuracy of CNN has not plateaued. A sensitivity analysis of the CNN model demonstrated its ability to determine important wavelengths region that affected the predictions of various soil attributes.

No abstract

No abstract

No abstract