Leveraging Gradient-Based Optimizer and Deep Learning for Automated Soil Classification Model

Soil classification is one of the emanating topics and major concerns in many countries.As the population has been increasing at a rapid pace,the demand for food also increases dynamically.Common approaches used by agriculturalists are inadequate to satisfy the rising demand,and thus they have hindered soil cultivation.There comes a demand for computer-related soil classification methods to support agriculturalists.This study introduces a Gradient-Based Optimizer and Deep Learning(DL)for Automated Soil Clas-sification(GBODL-ASC)technique.The presented GBODL-ASC technique identifies various kinds of soil using DL and computer vision approaches.In the presented GBODL-ASC technique,three major processes are involved.At the initial stage,the presented GBODL-ASC technique applies the GBO algorithm with the EfficientNet prototype to generate feature vectors.For soil categorization,the GBODL-ASC procedure uses an arithmetic optimization algorithm(AOA)with a Back Propagation Neural Network(BPNN)model.The design of GBO and AOA algorithms assist in the proper selection of parameter values for the EfficientNet and BPNN models,respectively.To demonstrate the significant soil classification outcomes of the GBODL-ASC methodology,a wide-ranging simulation analysis is performed on a soil dataset comprising 156 images and five classes.The simulation values show the betterment of the GBODL-ASC model through other models with maximum precision of 95.64%.

Indigenous Knowledge on Soil Classification of Ethnic Groups in Luang Prabang Province of the Lao PDR

The objectives of this study were to demonstrate ethno-scientific elicitation techniques in retrieving indigenous knowledge at village-level, and to document the indigenous soil classification systems of different ethnic groups in Luang Prabang province in the Lao PDR. The study area comprised three villages – Nambo, Huaymaha and Thapo, in the Phonxay district of Luang Prabang province. Three ethnic groups were covered by the study – Hmong, Khmu and Lao Loum. All three ethnic groups used soil color as main criteria for soil classification. However, even within the same ethnic group, sometimes different villages have differences in the way they classify soils; this was apparent for the Hmong ethnic group in the villages of Huaymaha and Nambo. A significant difference of the Lao Loum ethnic group from the other two, was the emphasis used in classifying soil types according to their water holding capabilities. In contrast, the Khmu and Hmong classified many soil types in relation to their rock content (‘with rock’ or ‘pure rock’ sometimesbeing used). The results of the study suggest that the ethnic groups classify the soils in relation to their potential for different types of agricultural production.

A case study on the soil classification of the Yellow River Delta based on piezocone penetration test

Piezocone penetration test(CPTu),the preferred in-situ tool for submarine investigation,is significant for soil classification and soil depth profile prediction,which can be used to predict soil types and states.However,the accuracy of these methods needs to be validated for local conditions.To distinguish and evaluate the properties of the shallow surface sediments in Chengdao area of the Yellow River Delta,seabed CPTu tests were carried out at ten stations in this area.Nine soil classification methods based on CPTu data are applied for soil classification.The results of classification are compared with the in-situ sampling to determine whether the method can provide sufficient resolution.The methods presented by Robertson(based on soil behavior type index Ic),Olsen and Mitchell are the more consistent and compatible ones compared with other methods.Considering that silt soils have potential to liquefy under storm tide or other adverse conditions,this paper is able to screen soil classification methods suitable for the Chengdao area and help identify the areas where liquefaction or submarine landslide may occur through CPTu investigation.

Discussion of“Site observations of weathered granitic soils subjected to cementation and partial drainage using SCPTU”[J Rock Mech Geotech Eng 15(2023)984e996]

Comprehensive data from in situ and laboratory tests in residual soil have been presented by Zhang et al.(2023).A number of issues addressed in the paper have been the interest of the discussers,namely the characterisation and behaviour of residual soils,limitation of piezocone testing due to the capacity of the entire system,measurement of shear wave velocity,rate effect of piezocone(CPTU)testing and piezocone testing with dual pore pressure penetrometers.Clarification and complementation of these issues are required with regard to both the execution and interpretation of the tests.

Study on strength properties and soil behaviour type classification of Huanghe River Delta silts based on variable rate piezocone penetration test

Fine-grained silt is widely distributed in the Huanghe River Delta(HRD)in China,and the sedimentary structure is complex,meaning that the clay content in the silt is variable.The piezocone penetration test(CPTu)is the most widely approved in situ test method.It can be used to invert soil properties and interpret soil behavior.To analyse the strength properties of surface sediments in the HRD,this paper evaluated the friction angle and its inversion formula through the CPTu penetration test and monotonic simple shear test and other soil unit experiments.The evaluation showed that the empirical formula proposed by Kulhawy and Mayne had better prediction and inversion effect.The HRD silts with clay contents of 9.2%,21.4%and 30.3%were selected as samples for the CPTu variable rate penetration test.The results show as follows.(1)The effects of the clay content on the tip resistance and the pore pressure of silt under different penetration rates were summarized.The tip resistance Q_t is strongly dependent on the clay content of the silt,the B_(q)value of the silt tends to 0 and is not significantly affected by the change of the CPTu penetration rate.(2)Five soil behavior type classification charts and three soil behavior type indexes based on CPTu data were evaluated.The results show that the soil behavior type classification chart based on soil behavior type index ISBT,the Robertson 2010 behavior type classification chart are more suitable for the silty soil in the HRD.

Groutability classification of granular soils with cement grouts

This research aims to develop a methodology for applying the geostatistical method to generate a groutability classification for granular soils.To ensure the precision of the suggested technique,a total of 103 data samples were used.Predicting the groutability of granular soils has always been difficult because of many soil characteristics.As a result,a new two-dimensional graph,the groutability classification of granular soil(GCS)chart,was developed.GCS establishment was based on data analysis of the grain size of soil and cement-based grouts(N1 and N2),relative density(Dr)and fines content of the soil(FC),water/cement ratio of grout mixture(w/c),and grouting pressure(P),all of which have a direct impact on the groutability of soil media.The geostatistical method was used to develop and compile the GCS graph based on the aforementioned parameters with the use of coefficient S,which is a coefficient of the scoring set of parameters including P,w/c,Dr,and FC.The validation process was carried out hierarchically,with an additional set of 30 data.The proposed method has a prediction accuracy of roughly 96.7%,demonstrating a helpful tool.The proposed approach can be easily implemented in practical engineering situations because it has a comparable syntax to commonly used formulae.It should be noted that the proposed formula was only tested using the data samples collected,and the applicability of the produced procedure to other situations requires more examination.

Chinese Soil Taxonomy:A Milestone of Soil Classification in China

1 Background Taxonomy is the branch of science dedicated to discovering,characterizing,naming,and classifying objects or organisms so as to understand relationships between them and the factors of their formation.The aims of classification are to identify and understand the objects for establishing an orderly system for the grouping objects.

Characterization of Some Typical Soils of the Miombo Woodland Ecosystem of Kitonga Forest Reserve, Iringa, Tanzania： Physico-Chemical Properties and Classification

Despite the fact that miombo woodland soils have significant implications in global climate change processes, few studies have been done to characterize and classify the soils of the miombo woodland ecosystem of Tanzania. The current study was carried out to map and classify soils of Kitonga Forest Reserve, which is a typical miombo woodland ecosystem, in order to generate relevant information for their use and management. A representative study area of 52 km2 was selected and mapped at a scale of 1：50,000 on the basis of relief. Ten representative soil profiles were excavated and described using standard methods. Soil samples were taken from genetic soil horizons and analyzed in the laboratory for physico-chemical characteristics using standard methods. Using field and laboratory analytical data, the soils were classified according to the FAO-World Reference Base （FAO-WRB） for Soil Resources system as Cambisols, Leptosols and Fluvisols. In the USDA-NRCS Soil Taxonomy system the soils were classified as Inceptisols and Entisols. Topographical features played an important role in soil formation. The different soil types differed in physico-chemical properties, hence exhibit differences in their potentials, constraints and need specific management strategies. Texture varied from sandy to different loams; pH from 5.1 to 5.9; organic carbon from 0.9 g/kg to 20 g/kg; and CEC from 3 cmol/（＋）kg to 24 cmol/（＋）kg. Sustainable management of miombo woodlands ecosystem soils requires reduced deforestation and reduced land degradation.

Site observations of weathered granitic soils subjected to cementation and partial drainage using SCPTU

Because of the cementation inherited from the parent rock,weathered granitic soil is usually susceptible to disturbance,which poses considerable challenges for laboratory characterization.The cone penetration test with pore pressure measurements has long been known for its reliability in site investigations and stratigraphic profiling.However,although extensive piezocone test results and experience are available for sedimentary soil,similar advances are yet to be made for weathered granitic soil.Moreover,the experience from sedimentary soil may not be directly applicable to weathered profiles because of the essentially different natures of the two types of geomaterials.This study performs seismic piezocone tests in a weathered granitic profile comprising residual granitic soil,completely weathered granite,and highly weathered granite.Pore pressure is measured at both the cone mid-face and the shoulder,and the effects of penetrometer size and penetration rate are considered.A series of updated soil behavior type charts is proposed to interpret the test results,thereby allowing the effect of weathering to be evaluated.This paper offers an important extension to the sparse data on the in situ responses of weathered materials.

Geotechnical Identification and Classification of Soils as Flexible Pavement Subgrade of the Section Fongo Tongo-Melong

The present study is inscribed within the framework of the geotechnical characterization of the soils of the Santchou plain, their classification for employment as pavement subgrade, various identification tests were carried out on the samples. The results obtained showed that with a wide range of different grain sizes, the studied soils showed low content in clay grains and dominance of either sand grains or silt grains, this can be explaining how most of these soil are poorly graded. According to the USDA textural classification, the grain size distribution of these soils makes them to be classified as Silty Loam types to Sandy Loam types. Despite of their organic matter content which is less than 10%, according to their respective methylene blue values, the soils studied along the section should be mainly loamy soil of medium plasticity to clayed soil, therefore showing a sensibility of its behavior to variation of water content. That last one is confirmed by the consistency parameters of these soils which show intermediate plasticity to highly plastic. Also, the bearing capacity proposed by these soils at their respective optimum dry densities is relatively small, although most of these experimental CBR values of the studied soils are more important than the ones prescribed by the AASHTO Classification system for A5, A6, and A7 types, and the French Highway Earthworks Manual Classifications system (GTR) for the corresponding A2 and A3 types.

Comparative analysis on soil engineering classifications of China and America

Based on China National Standard of Soil Engineering Classification (GB/T 50145-2007) and the Unified Soil Classification System of American Society for Testing Materials (ASTM D-2478), two kinds of soil laboratory engineering classification methods were discussed and analyzed from the aspects of the definition in particle fraction, classification of soil type and evaluation standard for soil gradation. There is a same limit of fine grains fraction in the two standards, and there are three main types of soil in GB/T 50145-2007 and two in ASTM D-2487. Different evaluation standards of gradation are put forward for gravels and sands in ASTM D-2487. Same criteria of A line, B line and controlling value of plastic index are in the plasticity chart of both standards.

Hyper-spectral characteristics and classification of farmland soil in northeast of China

The physical and chemical heterogeneities of soils make the soil spectral different and complicated, and it is valuable to increase the accuracy of prediction models for soil organic matter（SOM） based on pre-classification. This experiment was conducted under a controllable environment, and different soil samples from northeast of China were measured using ASD2500 hyperspectral instrument. The results showed that there are different reflectances in different soil types. There are statistically significant correlation between SOM and reflectence at 0.05 and 0.01 levels in 550–850 nm, and all soil types get significant at 0.01 level in 650–750 nm. The results indicated that soil types of the northeast can be divided into three categories： The first category shows relatively flat and low reflectance in the entire band; the second shows that the spectral reflectance curve raises fastest in 460–610 nm band, the sharp increase in the slope, but uneven slope changes; the third category slowly uplifts in the visible band, and its slope in the visible band is obviously higher than the first category. Except for the classification by curve shapes of reflectance, principal component analysis is one more effective method to classify soil types. The first principal component includes 62.13–97.19% of spectral information and it mainly relates to the information in 560–600, 630–690 and 690–760 nm. The second mainly represents spectral information in 1 640–1 740, 2 050–2 120 and 2 200–2 300 nm. The samples with high OM are often in the left, and the others with low OM are in the right of the scatter plot（the first principal component is the horizontal axis and the second is the longitudinal axis）. Soil types in northeast of China can be classified effectively by those two principles; it is also a valuable reference to other soil in other areas.

APPLYING PPE MODEL BASED ON RAGA TO CLASSIFYAND EVALUATE SOIL GRADE

The research of soil classification and soil grade evaluation is often based on fuzzy theory. So, the traditional method has an inevitable problem about weight matrix which given by some experts, and the final result can be influenced by artificial factors. The essentials of fuzzy synthetically judge is to handle the data of high dimension. That is to reducing the dimension number. The weight matrix in fuzzy theory is corresponding to low dimension projection value of each index. But we can′t define whether the weight matrix given by experts is the best projection value or not. So, the authors apply a new technique of falling dimension named projection pursuit to soil study, through using the improved real coding based accelerating genetic algorithm to optimize the projection direction. Thus, it can transfer multi dimension data into one dimension data, through searching for the optimum projection direction to realize the soil classification and its grade evaluation. The method can avoid the artificial disturbance, and acquire preferably effect. Thus, the paper provides a new method to the research of soil classification and grade evaluation.

A stochastic based approach for a new site classification method:application to the Algerian seismic code

Building codes have widely considered the shear wave velocity to make a reliable subsoil seismic classification, based on the knowledge of the mechanical properties of material deposits down to bedrock. This approach has limitations because geophysical data are often very expensive to obtain. Recently, other alternatives have been proposed based on measurements of background noise and estimation of the H/V amplification curve. However, the use of this technique needs a regulatory framework before it can become a realistic site classification procedure. This paper proposes a new formulation for characterizing design sites in accordance with the Algerian seismic building code (RPA99/ver.2003), through transfer functions, by following a stochastic approach combined to a statistical study. For each soil type, the deterministic calculation of the average transfer function is performed over a wide sample of 1-D soil profiles, where the average shear wave (S-W) velocity, Vs, in soil layers is simulated using random field theory. Average transfer functions are also used to calculate average site factors and normalized acceleration response spectra to highlight the amplification potential of each site type, since frequency content of the transfer function is significantly similar to that of the H/V amplification curve. Comparison is done with the RPA99/ver.2003 and Eurocode8 (EC8) design response spectra, respectively. In the absence of geophysical data, the proposed classification approach together with micro-tremor measures can be used toward a better soil classification.

Multiclass stand-alone and ensemble machine learning algorithms utilised to classify soils based on their physico-chemical characteristics

This study has provided an approach to classify soil using machine learning.Multiclass elements of stand-alone machine learning algorithms(i.e.logistic regression(LR)and artificial neural network(ANN)),decision tree ensembles(i.e.decision forest(DF)and decision jungle(DJ)),and meta-ensemble models(i.e.stacking ensemble(SE)and voting ensemble(VE))were used to classify soils based on their intrinsic physico-chemical properties.Also,the multiclass prediction was carried out across multiple cross-validation(CV)methods,i.e.train validation split(TVS),k-fold cross-validation(KFCV),and Monte Carlo cross-validation(MCCV).Results indicated that the soils’clay fraction(CF)had the most influence on the multiclass prediction of natural soils’plasticity while specific surface and carbonate content(CC)possessed the least within the nature of the dataset used in this study.Stand-alone machine learning models(LR and ANN)produced relatively less accurate predictive performance(accuracy of 0.45,average precision of 0.5,and average recall of 0.44)compared to tree-based models(accuracy of 0.68,average precision of 0.71,and recall rate of 0.68),while the meta-ensembles(SE and VE)outperformed(accuracy of 0.75,average precision of 0.74,and average recall rate of 0.72)all the models utilised for multiclass classification.Sensitivity analysis of the meta-ensembles proved their capacities to discriminate between soil classes across the methods of CV considered.Machine learning training and validation using MCCV and KFCV methods enabled better prediction while also ensuring that the dataset was not overfitted by the machine learning models.Further confirmation of this phenomenon was depicted by the continuous rise of the cumulative lift curve(LC)of the best performing models when using the MCCV technique.Overall,this study demonstrated that soil’s physico-chemical properties do have a direct influence on plastic behaviour and,therefore,can be relied upon to classify soils.

CLASSIFICATION OF CRYOSOLS?SIGNIFICANCE,ACHIEVEMENTS AND CHALLENGES

International concerns about the effects of global change on permafrost-affected soils and responses of permafrost terrestrial landscapes to such change have been increasing in the last two decades. To achieve a variety of goals including the determining of soil carbon stocks and dynamics in the Northern Hemisphere,the understanding of soil degradation and the best ways to protect the fragile ecosystems in permafrost environment,further study development on Cryosol classification is being in great demand. In this paper the existing Cryosol classifications contained in three representative soil taxonomies are introduced,and the problems in the practical application of the defining criteria used for category differentiation in these taxonomic systems are discussed. Meanwhile,the resumption and reconstruction of Chinese Cryosol classification within a taxonomic frame is proposed. In dealing with Cryosol classification the advantages that Chinese pedologists have and the challenges that they have to face are analyzed. Finally,several suggestions on the study development of the further taxonomic frame of Cryosol classification are put forward.

Numerical Approaches to Identification of Characteristic Soil Layers in an Urban Environment

Pedogenetic soil horizons are one of the fundamental building blocks of modern soil classification; however, in soils of urban areas which are often strongly disturbed by human activities, horizons are difficult to distinguish but substitutive morphological layers may be identified. To identify the characteristic soil layers in an urban environment, 224 soil layers of 36 in-situ pedons were examined and described in urban and suburban Nanjing, and 27 variables were extracted for multivariate analysis. Three groups and six subdivisions were identified by TwoStep cluster analysis combined with hierarchical cluster analysis based on factor scores. Soil forming factors and soil forming processes could be interpreted from the principal component analysis （PCA） of variables, cluster analysis of soil layers, and discriminant analysis of soil layer groups and their subdivisions. Parent materials, moisture regimes, organic matter accumulation, and especially nutrient accumulation were the main causes of characteristic soil layer formations. The numerical approaches used in this study were useful tools for characteristic soil layer identification of urban soils.

Evaluation of the Effect of Lime Content on the California Bearing Ratio of Silty Soils: Case of Fombap District

The present study is inscribed within the framework of the amelioration of the soils of the Santchou plain for employment as pavement subgrade. The bearing capacity proposed by these soils at their respective optimum dry densities is relatively small, although most of these experimental California Bearing Ratio (CBR) values of the studied soils are more important than the ones prescribed by the American Association of State Highway and Transportation Officials Classification system (AASHTO) for A5, A6, and A7 types. The stabilization of this soils with lime has been chosen to improve the bearing capacity and by association, their resilient modulus. The results of this study show that the increase of lime content is not proportional with the increase of the expected mechanical performances. In fact, the literature explains that when the lime content arrives at an optimum, the mechanical parameters no longer increase, but decrease significantly. After this optimum, the soil stabilization no longer shows advantages in the increase of geo-mechanical properties of soils.

Soil and Land Suitability Assessment for Rice Cultivation at Tono Irrigation Area in the Upper East Region, Ghana

Agriculture is one of the livelihood supports for the people of Upper East Region of Ghana. Soil evaluation research was conducted at Tono Irrigation Scheme to assess soil and land suitability for rice cultivation in the irrigable area of Tono Irrigation Scheme. A total of eleven (11) soil samples were collected and analysed for their chemical and physical properties. Based on field observation and criteria for soil suitability assessment, the different soil types that were identified were classified at the series level based on their position, parent material and the observed physical characteristics. The results indicated that the pH of the soils was within the acceptable range for crop production;however, the overall fertility level of the soils was very low. Physically, the upland soils were well to moderately well-drained, consisting of coarse-grained sandy loams topsoil overlying similar sandy loams and sandy clay loams at depth. They included Leptosols and Lixisols. The soils of the Scheme under lowlands and valley bottom sites, however, included Eutric Gleysol, Calsic Vertisol, Eutric Fluvisol and Eutric Plinthosol, which were heavily textured and relatively poor drained, or medium-textured and moderately to imperfectly well-drained. They showed a low to a very low rate of water percolation losses, which is good for the current farming system of cropping rice within the lowlands and valley bottom sites of the Scheme.

Morphological and Physico-Chemical Characteristics and Classification of Vertisol Developed on Deltaic Plain

The name of Vertisol is derived from Latin “vertere” meaning to invert. This case restricts development of soil horizons in profile. These soils have the capacity to swell and shrink, inducing cracks in the upper parts of the soil and distinctive soil structure throughout the soil. The formation of these specific features are caused by a heavy texture, a dominance of swelling clay in the fine fraction and marked changes in moisture content. The swell-shrink behavior is attributed to the wetting and drying of the soil mass. In this study, morphology, physico-chemical characteristics and classification of vertisols that were formed on alluvial delta plains, were investigated. Those soils formed on the Bafra Plain found in the K?z?l?rmak Delta and located in the central Black Sea region of Turkey. All studied Vertisols are characterised by a dark colour in surface soil, a heavy clayey texture, hardpan formation under top soil (high bulk density a high compaction) and very high COLE values. In addition, they have deep wide-opened desiccation cracks at the surface, slickensides at the middle part of the profiles and a poor differentiation of their horizons. Physico-chemically, the studied soils are slightly basic to very basic, non-saline and poor in organic matter, which is slightly higher in the surface horizon. In addition, cation exchange capacity, sum of exchangeable bases and base saturation of soils are very high. On the basis of morphological and physicochemical analysis, soil profiles were classified as Sodic Haplustert, Typic Calciaquert, Sodic Calciustert according to Soil Taxonomy (Soil Survey Staff, 1975 and 1999) and as Sodic Vertisol and Calcic Vertisol according to FAO/ISRIC (2006) classification systems.