Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space

Understanding the spatial distribution of soil organic carbon (SOC) content over different climatic regions will enhance our knowledge of carbon gains and losses due to climatic change. However, little is known about the SOC content in the contrasting arid and sub-humid regions of Iran, whose complex SOC–landscape relationships pose a challenge to spatial analysis. Machine learning (ML) models with a digital soil mapping framework can solve such complex relationships. Current research focusses on ensemble ML models to increase the accuracy of prediction. The usual ensemble method is boosting or weighted averaging. This study proposes a novel ensemble technique: the stacking of multiple ML models through a meta-learning model. In addition, we tested the ensemble through rescanning the covariate space to maximize the prediction accuracy. We first applied six state-of-the-art ML models (i.e., Cubist, random forests (RF), extreme gradient boosting (XGBoost), classical artificial neural network models (ANN), neural network ensemble based on model averaging (AvNNet), and deep learning neural networks (DNN)) to predict and map the spatial distribution of SOC content at six soil depth intervals for both regions. In addition, the stacking of multiple ML models through a meta-learning model with/without rescanning the covariate space were tested and applied to maximize the prediction accuracy. Out of six ML models, the DNN resulted in the best modeling accuracies, followed by RF, XGBoost, AvNNet, ANN, and Cubist. Importantly, the stacking of models indicated a significant improvement in the prediction of SOC content, especially when combined with rescanning the covariate space. For instance, the RMSE values for SOC content prediction of the upper 0–5 cm of the soil profiles of the arid site and the sub-humid site by the proposed stacking approaches were 17% and 9% respectively, less than that obtained by the DNN models—the best individual model. This indicates that rescanning the original covariate space by a meta-learning model can extract more information and improve the SOC content prediction accuracy. Overall, our results suggest that the stacking of diverse sets of models could be used to more accurately estimate the spatial distribution of SOC content in different climatic regions.

Download Full-text

Predicting Sentiment Polarity of Microblogs using an LSTM – CNN Deep Learning Model

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f8933.088619 ◽

2019 ◽

Vol 8 (6) ◽

pp. 4368-4373

Keyword(s):

Neural Network ◽

Machine Learning ◽

Prediction Accuracy ◽

Short Term Memory ◽

Learning Model ◽

Supervised Machine Learning ◽

Machine Learning Model ◽

Proposed Model ◽

Network Approaches

In this paper we propose a novel supervised machine learning model to predict the polarity of sentiments expressed in microblogs. The proposed model has a stacked neural network structure consisting of Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) layers. In order to capture the long-term dependencies of sentiments in the text ordering of a microblog, the proposed model employs an LSTM layer. The encodings produced by the LSTM layer are then fed to a CNN layer, which generates localized patterns of higher accuracy. These patterns are capable of capturing both local and global long-term dependences in the text of the microblogs. It was observed that the proposed model performs better and gives improved prediction accuracy when compared to semantic, machine learning and deep neural network approaches such as SVM, CNN, LSTM, CNN-LSTM, etc. This paper utilizes the benchmark Stanford Large Movie Review dataset to show the significance of the new approach. The prediction accuracy of the proposed approach is comparable to other state-of-art approaches.

Download Full-text

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

10.26434/chemrxiv.9894224.v1 ◽

2019 ◽

Author(s):

Ryther Anderson ◽

Achay Biong ◽

Diego Gómez-Gualdrón

Keyword(s):

Neural Network ◽

Machine Learning ◽

Molecular Simulation ◽

Large Scale ◽

Learning Model ◽

Operating Conditions ◽

Small Subset ◽

Screening Methods ◽

Large Set ◽

Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

Download Full-text

The application of machine learning algorithms in predicting soil organic carbon/matter

10.31274/etd-20200624-203 ◽

2020 ◽

Author(s):

Yones Khaledian

Keyword(s):

Machine Learning ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Carbon Matter

Download Full-text

Influence of Slope Gradient and Aspect on Soil Organic Carbon Content in the Region of Niš, Serbia

Sustainability ◽

10.3390/su13158332 ◽

2021 ◽

Vol 13 (15) ◽

pp. 8332

Author(s):

Snežana Jakšić ◽

Jordana Ninkov ◽

Stanko Milić ◽

Jovica Vasin ◽

Milorad Živanov ◽

...

Keyword(s):

Land Use ◽

Spatial Distribution ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Slope Aspect ◽

Available Phosphorus ◽

Organic Carbon Content ◽

Slope Gradient ◽

Phosphorus And Potassium ◽

Uncultivated Land

Topography-induced microclimate differences determine the local spatial variation of soil characteristics as topographic factors may play the most essential role in changing the climatic pattern. The aim of this study was to investigate the spatial distribution of soil organic carbon (SOC) with respect to the slope gradient and aspect, and to quantify their influence on SOC within different land use/cover classes. The study area is the Region of Niš in Serbia, which is characterized by complex topography with large variability in the spatial distribution of SOC. Soil samples at 0–30 cm and 30–60 cm were collected from different slope gradients and aspects in each of the three land use/cover classes. The results showed that the slope aspect significantly influenced the spatial distribution of SOC in the forest and vineyard soils, where N- and NW-facing soils had the highest level of organic carbon in the topsoil. There were no similar patterns in the uncultivated land. No significant differences were found in the subsoil. Organic carbon content was higher in the topsoil, regardless of the slope of the terrain. The mean SOC content in forest land decreased with increasing slope, but the difference was not statistically significant. In vineyards and uncultivated land, the SOC content was not predominantly determined by the slope gradient. No significant variations across slope gradients were found for all observed soil properties, except for available phosphorus and potassium. A positive correlation was observed between SOC and total nitrogen, clay, silt, and available phosphorus and potassium, while a negative correlation with coarse sand was detected. The slope aspect in relation to different land use/cover classes could provide an important reference for land management strategies in light of sustainable development.

Download Full-text

Topographic Position, Land Use and Soil Management Effects on Soil Organic Carbon (Vineyard Region of Niš, Serbia)

Agronomy ◽

10.3390/agronomy11071438 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1438

Author(s):

Snežana Jakšić ◽

Jordana Ninkov ◽

Stanko Milić ◽

Jovica Vasin ◽

Milorad Živanov ◽

...

Keyword(s):

Land Use ◽

Surface Layer ◽

Spatial Distribution ◽

Soil Erosion ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Soil Compaction ◽

Soil Management ◽

Forest Land ◽

Topographic Position

Spatial distribution of soil organic carbon (SOC) is the result of a combination of various factors related to both the natural environment and anthropogenic activities. The aim of this study was to examine (i) the state of SOC in topsoil and subsoil of vineyards compared to the nearest forest, (ii) the influence of soil management on SOC, (iii) the variation in SOC content with topographic position, (iv) the intensity of soil erosion in order to estimate the leaching of SOC from upper to lower topographic positions, and (v) the significance of SOC for the reduction of soil’s susceptibility to compaction. The study area was the vineyard region of Niš, which represents a medium-sized vineyard region in Serbia. About 32% of the total land area is affected, to some degree, by soil erosion. However, according to the mean annual soil loss rate, the total area is classified as having tolerable erosion risk. Land use was shown to be an important factor that controls SOC content. The vineyards contained less SOC than forest land. The SOC content was affected by topographic position. The interactive effect of topographic position and land use on SOC was significant. The SOC of forest land was significantly higher at the upper position than at the middle and lower positions. Spatial distribution of organic carbon in vineyards was not influenced by altitude, but occurred as a consequence of different soil management practices. The deep tillage at 60–80 cm, along with application of organic amendments, showed the potential to preserve SOC in the subsoil and prevent carbon loss from the surface layer. Penetrometric resistance values indicated optimum soil compaction in the surface layer of the soil, while low permeability was observed in deeper layers. Increases in SOC content reduce soil compaction and thus the risk of erosion and landslides. Knowledge of soil carbon distribution as a function of topographic position, land use and soil management is important for sustainable production and climate change mitigation.

Download Full-text

Estimating soil organic carbon stock change at multiple scales using machine learning and multivariate geostatistics

Geoderma ◽

10.1016/j.geoderma.2021.115356 ◽

2021 ◽

Vol 403 ◽

pp. 115356

Author(s):

Gábor Szatmári ◽

László Pásztor ◽

Gerard B.M. Heuvelink

Keyword(s):

Machine Learning ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Carbon Stock ◽

Multiple Scales ◽

Multivariate Geostatistics ◽

Soil Organic Carbon Stock ◽

Carbon Stock Change ◽

Organic Carbon Stock ◽

Stock Change

Download Full-text

Digital Mapping of Soil Organic Carbon Using Sentinel Series Data: A Case Study of the Ebinur Lake Watershed in Xinjiang

Remote Sensing ◽

10.3390/rs13040769 ◽

2021 ◽

Vol 13 (4) ◽

pp. 769

Author(s):

Xiaohang Li ◽

Jianli Ding ◽

Jie Liu ◽

Xiangyu Ge ◽

Junyong Zhang

Keyword(s):

Remote Sensing ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Prediction Accuracy ◽

Lake Basin ◽

Arid Areas ◽

Annual Average ◽

Machine Learning Methods ◽

Ebinur Lake ◽

Ebinur Lake Basin

As an important evaluation index of soil quality, soil organic carbon (SOC) plays an important role in soil health, ecological security, soil material cycle and global climate cycle. The use of multi-source remote sensing on soil organic carbon distribution has a certain auxiliary effect on the study of soil organic carbon storage and the regional ecological cycle. However, the study on SOC distribution in Ebinur Lake Basin in arid and semi-arid regions is limited to the mapping of measured data, and the soil mapping of SOC using remote sensing data needs to be studied. Whether different machine learning methods can improve prediction accuracy in mapping process is less studied in arid areas. Based on that, combined with the proposed problems, this study selected the typical area of the Ebinur Lake Basin in the arid region as the study area, took the sentinel data as the main data source, and used the Sentinel-1A (radar data), the Sentinel-2A and the Sentinel-3A (multispectral data), combined with 16 kinds of DEM derivatives and climate data (annual average temperature MAT, annual average precipitation MAP) as analysis. The five different types of data are reconstructed by spatial data and divided into four spatial resolutions (10, 100, 300, and 500 m). Seven models are constructed and predicted by machine learning methods RF and Cubist. The results show that the prediction accuracy of RF model is better than that of Cubist model, indicating that RF model is more suitable for small areas in arid areas. Among the three data sources, Sentinel-1A has the highest SOC prediction accuracy of 0.391 at 10 m resolution under the RF model. The results of the importance of environmental variables show that the importance of Flow Accumulation is higher in the RF model and the importance of SLOP in the DEM derivative is higher in the Cubist model. In the prediction results, SOC is mainly distributed in oasis and regions with more human activities, while SOC is less distributed in other regions. This study provides a certain reference value for the prediction of small-scale soil organic carbon spatial distribution by means of remote sensing and environmental factors.

Download Full-text