Mapping of soil organic carbon using machine learning models: Combination of optical and radar remote sensing data

Accurate high-resolution yield maps are essential for identifying spatial yield variability patterns, determining key factors influencing yield variability, and providing site-specific management insights in precision agriculture. Cultivar differences can significantly influence potato (Solanum tuberosum L.) tuber yield prediction using remote sensing technologies. The objective of this study was to improve potato yield prediction using unmanned aerial vehicle (UAV) remote sensing by incorporating cultivar information with machine learning methods. Small plot experiments involving different cultivars and nitrogen (N) rates were conducted in 2018 and 2019. UAV-based multi-spectral images were collected throughout the growing season. Machine learning models, i.e., random forest regression (RFR) and support vector regression (SVR), were used to combine different vegetation indices with cultivar information. It was found that UAV-based spectral data from the early growing season at the tuber initiation stage (late June) were more correlated with potato marketable yield than the spectral data from the later growing season at the tuber maturation stage. However, the best performing vegetation indices and the best timing for potato yield prediction varied with cultivars. The performance of the RFR and SVR models using only remote sensing data was unsatisfactory (R2 = 0.48–0.51 for validation) but was significantly improved when cultivar information was incorporated (R2 = 0.75–0.79 for validation). It is concluded that combining high spatial-resolution UAV images and cultivar information using machine learning algorithms can significantly improve potato yield prediction than methods without using cultivar information. More studies are needed to improve potato yield prediction using more detailed cultivar information, soil and landscape variables, and management information, as well as more advanced machine learning models.

Download Full-text

Spatial soil organic carbon (SOC) prediction by regression kriging using remote sensing data

The Egyptian Journal of Remote Sensing and Space Science ◽

10.1016/j.ejrs.2016.06.004 ◽

2017 ◽

Vol 20 (1) ◽

pp. 61-70 ◽

Cited By ~ 27

Author(s):

Arun Mondal ◽

Deepak Khare ◽

Sananda Kundu ◽

Surajit Mondal ◽

Sandip Mukherjee ◽

...

Keyword(s):

Remote Sensing ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Remote Sensing Data ◽

Regression Kriging ◽

Sensing Data

Download Full-text

Mapping Soil Organic Carbon for Airborne and Simulated EnMAP Imagery Using the LUCAS Soil Database and a Local PLSR

Remote Sensing ◽

10.3390/rs12203451 ◽

2020 ◽

Vol 12 (20) ◽

pp. 3451

Author(s):

Kathrin J. Ward ◽

Sabine Chabrillat ◽

Maximilian Brell ◽

Fabio Castaldi ◽

Daniel Spengler ◽

...

Keyword(s):

Remote Sensing ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Prediction Accuracy ◽

Remote Sensing Data ◽

Soil Samples ◽

Wet Chemistry ◽

Sensing Data ◽

Soil Database ◽

Local Soil

Soil degradation is a major threat for European soils and therefore, the European Commission recommends intensifying research on soil monitoring to capture changes over time and space. Imaging spectroscopy is a promising technique to create spatially accurate topsoil maps based on hyperspectral remote sensing data. We tested the application of a local partial least squares regression (PLSR) to airborne HySpex and simulated satellite EnMAP (Environmental Mapping and Analysis Program) data acquired in north-eastern Germany to quantify the soil organic carbon (SOC) content. The approach consists of two steps: (i) the local PLSR uses the European LUCAS (land use/cover area frame statistical survey) Soil database to quantify the SOC content for soil samples from the study site in order to avoid the need for wet chemistry analyses, and subsequently (ii) a remote sensing model is calibrated based on the local PLSR SOC results and the corresponding image spectra. This two-step approach is compared to a traditional PLSR approach using measured SOC contents from local samples. The prediction accuracy is high for the laboratory model in the first step with R2 = 0.86 and RPD = 2.77. The HySpex airborne prediction accuracy of the traditional approach is high and slightly superior to the two-step approach (traditional: R2 = 0.78, RPD = 2.19; two-step: R2 = 0.67, RPD = 1.79). Applying the two-step approach to simulated EnMAP imagery leads to a lower but still reasonable prediction accuracy (traditional: R2 = 0.77, RPD = 2.15; two-step: R2 = 0.48, RPD = 1.41). The two-step models of both sensors were applied to all bare soils of the respective images to produce SOC maps. This local PLSR approach, based on large scale soil spectral libraries, demonstrates an alternative to SOC measurements from wet chemistry of local soil samples. It could allow for repeated inexpensive SOC mapping based on satellite remote sensing data as long as spectral measurements of a few local samples are available for model calibration.

Download Full-text

Mapping soil organic carbon in Tuscany through the statistical combination of ground observations with ancillary and remote sensing data

Geoderma ◽

10.1016/j.geoderma.2021.115386 ◽

2021 ◽

Vol 404 ◽

pp. 115386

Author(s):

Lorenzo Gardin ◽

Marta Chiesi ◽

Luca Fibbi ◽

Fabio Maselli

Keyword(s):

Remote Sensing ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Remote Sensing Data ◽

Sensing Data

Download Full-text

Multispectral Remote Sensing Data Are Effective and Robust in Mapping Regional Forest Soil Organic Carbon Stocks in a Northeast Forest Region in China

Remote Sensing ◽

10.3390/rs12030393 ◽

2020 ◽

Vol 12 (3) ◽

pp. 393 ◽

Cited By ~ 2

Author(s):

Shuai Wang ◽

Jinhu Gao ◽

Qianlai Zhuang ◽

Yuanyuan Lu ◽

Hanlong Gu ◽

...

Keyword(s):

Remote Sensing ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Forest Ecosystems ◽

Remote Sensing Data ◽

Variable Model ◽

Great Opportunity ◽

Sensing Data ◽

Multispectral Remote Sensing ◽

Soc Stocks

Accurately mapping the spatial distribution information of soil organic carbon (SOC) stocks is a key premise for soil resource management and environment protection. Rapid development of satellite remote sensing provides a great opportunity for monitoring SOC stocks at a large scale. In this study, based on 12 environmental variables of multispectral remote sensing, topography and climate and 236 soil sampling data, three different boosted regression tree (BRT) models were compared to obtain the most accurate map of SOC stocks covering the forest area of Lvshun District in the Northeast China. Four validation indexes, including mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Lin’s concordance correlation coefficient (LCCC) were calculated to evaluate the performance of the three models. The results showed that the full variable model performed the best, except the model using multispectral remote sensing variables. In the full variable model, the regional SOC stocks are primarily determined by multispectral remote sensing variables, followed by topographic and climatic variables, with the relative importance of variables in the model being 63%, 28%, and 9%, respectively. The average prediction results of full variables model and only multispectral remote sensing variables model were 8.99 and 9.32 kg m−2, respectively. Our results indicated that there is a strong dependence of SOC stocks on multispectral remote sensing data when forest ecosystems have dense natural vegetation. Our study suggests that the multispectral remote sensing variables should be used to map SOC stocks of forest ecosystems in our study region.

Download Full-text

Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models

Remote Sensing ◽

10.3390/rs13040641 ◽

2021 ◽

Vol 13 (4) ◽

pp. 641

Author(s):

Gopal Ramdas Mahajan ◽

Bappa Das ◽

Dayesh Murgaokar ◽

Ittai Herrmann ◽

Katja Berger ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Support Vector ◽

Spectral Indices ◽

Learning Models ◽

Leaf Nutrients ◽

Machine Learning Models

Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R2 ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R2 ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R2 ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

Download Full-text

Mapping Allochemical Limestone Formations in Hazara, Pakistan Using Google Cloud Architecture: Application of Machine-Learning Algorithms on Multispectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10020058 ◽

2021 ◽

Vol 10 (2) ◽

pp. 58

Author(s):

Muhammad Fawad Akbar Khan ◽

Khan Muhammad ◽

Shahid Bashir ◽

Shahab Ud Din ◽

Muhammad Hanif

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Learning Algorithms ◽

Remote Sensing Data ◽

Kappa Coefficient ◽

Machine Learning Algorithms ◽

Landsat 8 ◽

Sensing Data ◽

Fossiliferous Limestone

Low-resolution Geological Survey of Pakistan (GSP) maps surrounding the region of interest show oolitic and fossiliferous limestone occurrences correspondingly in Samanasuk, Lockhart, and Margalla hill formations in the Hazara division, Pakistan. Machine-learning algorithms (MLAs) have been rarely applied to multispectral remote sensing data for differentiating between limestone formations formed due to different depositional environments, such as oolitic or fossiliferous. Unlike the previous studies that mostly report lithological classification of rock types having different chemical compositions by the MLAs, this paper aimed to investigate MLAs’ potential for mapping subclasses within the same lithology, i.e., limestone. Additionally, selecting appropriate data labels, training algorithms, hyperparameters, and remote sensing data sources were also investigated while applying these MLAs. In this paper, first, oolitic (Samanasuk), fossiliferous (Lockhart and Margalla) limestone-bearing formations along with the adjoining Hazara formation were mapped using random forest (RF), support vector machine (SVM), classification and regression tree (CART), and naïve Bayes (NB) MLAs. The RF algorithm reported the best accuracy of 83.28% and a Kappa coefficient of 0.78. To further improve the targeted allochemical limestone formation map, annotation labels were generated by the fusion of maps obtained from principal component analysis (PCA), decorrelation stretching (DS), X-means clustering applied to ASTER-L1T, Landsat-8, and Sentinel-2 datasets. These labels were used to train and validate SVM, CART, NB, and RF MLAs to obtain a binary classification map of limestone occurrences in the Hazara division, Pakistan using the Google Earth Engine (GEE) platform. The classification of Landsat-8 data by CART reported 99.63% accuracy, with a Kappa coefficient of 0.99, and was in good agreement with the field validation. This binary limestone map was further classified into oolitic (Samanasuk) and fossiliferous (Lockhart and Margalla) formations by all the four MLAs; in this case, RF surpassed all the other algorithms with an improved accuracy of 96.36%. This improvement can be attributed to better annotation, resulting in a binary limestone classification map, which formed a mask for improved classification of oolitic and fossiliferous limestone in the area.

Download Full-text