Machine Learning Approach to Simulate Soil CO2 Fluxes under Cropping Systems

With the growing number of datasets to describe greenhouse gas (GHG) emissions, there is an opportunity to develop novel predictive models that require neither the expense nor time required to make direct field measurements. This study evaluates the potential for machine learning (ML) approaches to predict soil GHG emissions without the biogeochemical expertise that is required to use many current models for simulating soil GHGs. There are ample data from field measurements now publicly available to test new modeling approaches. The objective of this paper was to develop and evaluate machine learning (ML) models using field data (soil temperature, soil moisture, soil classification, crop type, fertilization type, and air temperature) available in the Greenhouse gas Reduction through Agricultural Carbon Enhancement network (GRACEnet) database to simulate soil CO2 fluxes with different fertilization methods. Four machine learning algorithms—K nearest neighbor regression (KNN), support vector regression (SVR), random forest (RF) regression, and gradient boosted (GB) regression—were used to develop the models. The GB regression model outperformed all the other models on the training dataset with R2 = 0.88, MAE = 2177.89 g C ha−1 day−1, and RMSE 4405.43 g C ha−1 day−1. However, the RF and GB regression models both performed optimally on the unseen test dataset with R2 = 0.82. Machine learning tools were useful for developing predictors based on soil classification, soil temperature and air temperature when a large database like GRACEnet is available, but these were not highly predictive variables in correlation analysis. This study demonstrates the suitability of using tree-based ML algorithms for predictive modeling of CO2 fluxes, but no biogeochemical processes can be described with such models.

Pedometric tools for classification of southwestern Amazonian soils: A quali-quantitative interpretation incorporating visible-near infrared spectroscopy

The southwestern region of the Amazon has great environmental variability, presents a great complexity of pedoenvironments due to its rich variability of geological and geomorphological environments, as well as for being a transition region with other two Brazilian biomes. In this study, the use of pedometric tools (the Algorithms for Quantitative Pedology (AQP) R package and diffuse reflectance spectroscopy) was evaluated for the characterization of 15 soil profiles in southwestern Amazon. The AQP statistical package—which evaluates the soil in-depth based on slicing functions—indicated a wide range of variation in soil attributes, especially in the superficial horizons. In addition, the results obtained in the similarity analysis corroborated with the description of physical, chemical components and oxide contents in-depth, aiding the classification of soil profiles. The in-depth characterization of visible-near infrared spectra allowed inference of the pedogenetic processes of some profiles, setting precedents for future work aiming to establish analytical strategies for soil classification in southwestern Amazon based on spectral data.

Study The Consequence of Fly Ash on Some of Physical Soil Characteristics

Study the consequence of adding fly ash (FA) on the Atterberg limit; cohesions and internal friction of angles of the verified soil was the aim of this search. The tested soil according to the system of unified soil classification was (CH) group. Fly ash (FA) was added to the tested soil samples in 1, 3, 6, 9, 12, 15 & 18 % by weight of samples. This study shows that once the tested soil mixed with (FA); the values of cohesion reduced; while the values of the angles of internal frictions increases. The drop in the soil sample cohesion when mixed with 18% of (FA) was 34%, were noteworthy increase in the angles of internal friction. For all soil samples as the percentages of adding (FA) increase, the decrease in the index of plasticity amounts increase also at different rates. The adding of (FA) produced a reduction in the liquid limits; plastic limits and henceforth the plasticity index of the tested soil sample at rate of 43%, 48% and 37% correspondingly. The plasticity index losses took place at the first 3%, at a lesser rate, then the rate increased at 18% of additive and because nearly constant.

Development and Performance Evaluation of a Soil Moisture Sensor

This study was aimed at developing a soil moisture sensor to effectively monitor moisture level for optimum crop growth. The sensor was made using a programmed Arduino microcontroller. It is attached to a sensing panel with two probes made of nickel that measures the volumetric content of water in soil. The probes were non-corrosive and robust material suitable for use in wet surfaces. The developed sensor was tested and evaluated. The two legged Lead (probes) goes into the soil where water content was to be measured by passing current through the soil, and then reads the resistance to get the moisture level. Nine different soil classification samples (Sandy Clay, Fine Sandy Loam, Sandy Loam, Salty Loam, Loamy Sand, Coarse Sand, Fine Sand, Sandy Clay Loam and clay soils) at different depths (3, 6, 9, 12 and 14.3 cm) were used to analyse the moisture meter at three different portion of each soil sample. Results obtained indicates that there was a progressive increase in moisture levels the more the sensor was being dipped into the soil. Results obtained also shows that all the nine soil samples but one (Silt Loam Soil Sample) analysed were within acceptable range of accuracy (0.1 - 5.0 %). The moisture sensor whose cost was approximately #22,300:00 was found to be effective, high precision at less efforts and a suitable guide for farmer for determining soil moisture levels.Keywords- Moisture, Probe, Sensor, Soil Classification

Estimating cation exchange capacity and clay content from agricultural soil testing data

Clay content and the ability to reversibly retain cations affect many essential chemical and physical properties of soil, such as pH buffering and carbon sequestration. Cation exchange capacity (CEC) and base saturation are also commonly used as criteria in soil classification. However, determination of CEC and particle-size distribution is laborious and not included in routine soil testing. In this study, pedotransfer functions including soil test cations (STCat; Ca2+ + Mg2+ + K+), pH and soil organic carbon (SOC, %) as explanatory variables were developed for estimating CEC, titratable acidity (TA; H+ + Al3+) and clay content (clay, %). In addition, reference values for potential CEC and its components were determined for Finnish mineral and organic soils. The mean of potential CEC extracted by 1 M ammonium acetate at pH 7.0 ranged from 14 (range 6.4−25) in coarse soils to 33 (21−45) cmol(+) kg-1 in heavy clay soils, and from 42 (24−82) in mull soils to 77 (25−138) cmol(+) kg-1 in peat soils. The average CEC of clay and SOC were 27 and 160 cmol(+) kg-1, respectively. Titratable acidity occupied 53% and around 40% of the CEC sites in organic and mineral soils, respectively, evidencing that it is a prominent component of the potential CEC in these predominantly acidic soils. STCat, pH and SOC explained 96% of the variation in potential CEC. STCat and pH can be used in estimating the clay content especially for soils containing over 30% clay. In coarse textured soils, in contrast, SOC hampers the STCat based estimation of clay content.

K-means Based Soil Classification System Applicable to a Brazilian Mineral Province

This article presents a geotechnical soil classification system proposed for application on soils of a tropical mineral province, located in Minas Gerais state, Brazil. The system was constructed using data mining techniques, i.e., principal component analysis and k-means cluster analysis, which were applied to a dataset composed of 101 geotechnical characterization laboratory test results of soils from the Province of Quadrilátero Ferrífero. The main objective of the proposed soil classification method was to establish a regional soil classification system, which encompass the interpretability of the main geotechnical parameters of soils by means of the classification, given the little explanatory capacity of the Unified Soil Classification System classification system for the performance of such task. It was possible to establish a chart for soil classification capable of explaining 81.68% of the variability of the analyzed parameters, being established the soil classes A, B and C for the studied soils.

Evaluation of soil replacement and cement grout injection in soil settlement

This paper discusses the process of original soil stabilization in Trans Sumatra Bakauheni-Terbanggi Besar Toll Road Project Package 2 Sidomulyo-Kotabaru. The soil replacement process was conducted at approximately 24 kilometres along the toll’s main road. The original soil bearing capacity analysis stage was by performing a Dynamic Cone Penetrometer (DCP) and Sondir test to analyze the deep of hard soil. A soil replacement was carried out to replace the original soil with soil that has appropriate specification. the piling up process was conducted in stages, which has Sandstone in such of the layer. The research done about the landfill sample was retaken and collected at 68 points. The stockpile soil samples collection was then followed by the analysis which was conducted in the laboratory to find the soil bearing capacity. There are 4 types of bearing capacity parameters analyzed, namely specific gravity, water content, aggregate analysis (Sieve Analysis), and consistency limit (Atterberg Limit). Referring to it, then there was the classification of soil types according to AASHTO M145 & Casagrande Soil Classification System. A point that has settlement after soil replacement is STA 52+000. So, there need to add soil stabilization, that is cement grout injection. Researchers analyzed the soil settlement by interpretation method. Results showed that soil replacement and cement grout injection could decrease a soil settlement by about 15.07 cm to become 0.93 cm.

Forensic Study on Federal Road Pavement Failures at Rengit and Semerah, Batu Pahat

Forensic investigations in engineering term may be conducted to identify the causes of failure to facilitate the design of proper repairs, or to improve the performance or lifespan of a component, assembly, or structure. This paper presents the combination of geotechnical investigation and geophysical survey method as a forensic tool to predict the causes of pavement failure occurred along the coastal area of federal road FT005. The number and type of field testing are varying on each selected study area at Rengit and Semerah, Batu Pahat as this location constructed on soft soil area. Non-destructive testing (NDT) method using electrical resistivity tomography (ERT) were chosen to be applied at the worst severity of the road failure. Three number of resistivity lines of 100m and 200m were laid out using ABEM Terrameter LS2 with gradient method of electrode arrays covering up to 40-meters depth. Then, further testing of destructive testing (DT) method using borehole drilling conducted near the ERT lines to obtain soil profile with SPT N-value measurement. The disturbed and undisturbed samples were obtained to carried out laboratory test for soil classification. After that, inspection of road pavement layers were implemented at five number of trial pit tests which excavated up to subgrade layer to determine the thickness of the materials used in road construction. Three number of mackintosh probe test were also conducted on top of the subgrade layer after the trenching to obtain the strength of the subgrade layer. The results presented showed that severe longitudinal cracking were the predominant premature failures on the roads studied due to settlement effect of soft soil. The analysis obtained from RES2DINV program stated that the subsurface profiling was dominantly in saturated condition which the resistivity value was less than 100 ohm.m. From the SPT N-value it is observed that, the very soft soil layer is up to 8 m followed by the soft to stiff clays soil. Another cause of failure was resulted from the differential settlement due to the effect of different design of road construction with varies material used. The reliability and efficiency of the instruments used were also discussed in this study.