Soil Spectral Library Research Articles

Predicting USCS soil texture classes utilizing soil spectra and deep learning

Abstract Purpose Soil texture identification is vital for various agricultural and engineering applications but generally involves rigorous laboratory work, especially for estimating USCS (Unified Soil Classification System) soil texture classes. Soil texture influences soil water storage capacity, soil fertility, compaction characteristics, and soil strength. Soil spectroscopy offers a reliable approach that is non-destructive, rapid, and cost-effective to estimate several soil properties including texture. For engineering applications, the USCS soil texture classes are preferred, but very few studies have focussed on estimating USCS soil texture using soil spectroscopy or remote sensing data in general. Methods Two large soil spectral libraries (SSLs), viz., Kellog Soil Spectral Library (KSSL) and Open-source Soil Spectral Library (OSSL), as well as three deep learning algorithms (VGG-16, ResNet-16, and Swin transformers), were used in this study to predict six USCS soil texture classes and three USCS soil texture groups. The USCS soil texture classes and groups were derived by grouping clay, sand, and silt fractions that are closely associated with the corresponding USCS soil texture classes. Results The results indicate that the Swin transformer model performed the best with an accuracy of 67% for six USCS soil texture class predictions and 81% for three USCS soil texture group predictions. Cohen’s kappa value implies a moderate agreement (0.55) for soil texture class predictions and a substantial agreement (0.64) for soil texture group predictions. Conclusion The proposed methodology offers a novel approach for USCS soil texture class predictions utilizing SSLs and deep learning techniques.

Can Soil Spectroscopy be a Strong Alternative to the Conventional Methods of Analysis?

Soil is considered as the source of life on the globe. Although, numerous research studies, the soil is not completely understood whereas it is dynamic complex matrix include many simultaneous processes. The conventional methods of soil testing are the most reliable for assessing the land productivity and management. Unfortunately, these methods are time consuming and laborious as well as costly and hazardous to the environment. Therefore, the soil spectroscopy technique provides the functions of detecting, characterizing, quantifying and mapping several soil properties based on the uses of different kinds of the sensors (ground-based, airborne-based, and satellite-based). An integration of soil spectroscopic data, data processing, and modelling is considered as an effective tool for estimating soil parameters. Although these advanced techniques able to predict the majority of soil properties, there are some of these properties require more experiments for building accurate calibration models for estimation. Moreover, creating accurate soil spectral libraries (SSLs) for specific areas or soil types is very crucial for saving time, effort, expenses of soil surveying, sampling, and analysis. The application of these SSLs has a big limitation of the continuous variability of the soil properties over time. Thus, establishing extensive spectral libraries is important and mandatory for covering the small scaled areas’ variabilities as well as available soil types. Till now, the soil spectroscopy is not entirely replacing the conventional testing methods of soils because these techniques need future applications to be trusted and guaranteed of their effectiveness.

A Novel Transformer-CNN Approach for Predicting Soil Properties from LUCAS Vis-NIR Spectral Data

Soil, a non-renewable resource, requires continuous monitoring to prevent degradation and support sustainable agriculture. Visible-near-infrared (Vis-NIR) spectroscopy is a rapid and cost-effective method for predicting soil properties. While traditional machine learning methods are commonly used for modeling Vis-NIR spectral data, large datasets may benefit more from advanced deep learning techniques. In this study, based on the large soil spectral library LUCAS, we aimed to enhance regression model performance in soil property estimation by combining Transformer and convolutional neural network (CNN) techniques to predict 11 soil properties (clay, silt, pH in CaCl2, pH in H2O, CEC, OC, CaCO3, N, P, and K). The Transformer-CNN model accurately predicted most soil properties, outperforming other methods (partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), Long Short-Term Memory (LSTM), ResNet18) with a 10–24 percentage point improvement in the coefficient of determination (R2). The Transformer-CNN model excelled in predicting pH in CaCl2, pH in H2O, OC, CaCO3, and N (R2 = 0.94–0.96, RPD > 3) and performed well for clay, sand, CEC, P, and K (R2 = 0.77–0.85, 2 < RPD < 3). This study demonstrates the potential of Transformer-CNN in enhancing soil property prediction, although future work should aim to optimize computational efficiency and explore a wider range of applications to ensure its utility in different agricultural settings.

Advancing soil property prediction with encoder-decoder structures integrating traditional deep learning methods in Vis-NIR spectroscopy

The technology for estimating soil properties using visible and near-infrared spectroscopy has been maturing, with corresponding advances and breakthroughs in deep learning models. In this study, based on the large soil spectral library LUCAS, we explore the potential of encoder-decoder structures to improve convolutional neural network regression predictions. By introducing an encoder-decoder structure into the feature channels of a six-layer CNN model (TRNN model), we significantly enhanced the performance of shallow CNN models and successfully carried out regression predictions for seven soil properties. We employed IntegratedGradients, DeepLift, GradientShap, and DeepLiftShap methods to interpret the output of the TRNN model. Our TRNN model, built on raw spectra, demonstrated high accuracy in predicting multiple soil properties, outperforming residual architectures, LSTMs, various CNN architectures, and other traditional machine learning methods proposed in previous studies. We also investigated the impact of multi-task output structures (TRNN 1-M and TRNN M−M) and single-task output structures (TRNN 1-1) on model performance. For the TRNN model with an encoder-decoder structure, multi-task output structures resulted in a reduction in performance. The TRNN showed outstanding results in regression analysis of the seven soil properties selected in this study (cation exchange capacity, organic carbon content, calcium carbonate content, pH, clay content, silt content, and sand content), with R2 values exceeding 0.93 for all seven properties. Different soil characteristics correspond to different wavelengths, with multiple characteristic peaks commonly observed. This research convincingly demonstrates the enormous potential of combining large model architectures with traditional deep learning approaches for predicting soil properties, which could significantly advance precision agriculture.

Effects of Sample Handling on Visible and Near-Infrared Soil Reflectance

Soil reflectance is a cumulative attribute determined by interactions between light (photons) and the physical, chemical, and biological properties of soil. Soil properties such as organic matter, moisture, mineral oxide contents, soil texture, and surface roughness all influence soil reflectance at unique wavelengths. Many standard sample preparation techniques are designed to alter soil properties, so as to homogenize samples to improve the consistency of reflectance data collected. This study aims to quantify the effects of one standard sample preparation activity, drying, and repeated wetting–drying cycles on visible–near-infrared soil reflectance, by collecting reflectance data from nine samples which were dried then wetted for a total of three times. This study demonstrates the major, permanent effects of a drying and wetting cycle on soil reflectance, and then presents a model which can be used to correct for these effects. These results have direct implications for remote sensing activities, soil libraries, and soil spectral libraries. These results show that without correction, data from soil spectral libraries, spectral data collected from stored samples, and spectral data transferred between studies, have limited utility for characterizing soils as they exist in the field. Soil spectral data collected in the lab requires correction before it may be used to predict soil properties in the field, as standard sample handling procedures change intrinsic soil properties and introduce systematic error into these data.

Rapid soil attribute evaluation for soil security assessments in data-poor environments in the Pacific region

Many global environments face increasing pressures on soil resources, and effective, scalable methods for assessment of soil condition and capital are essential to respond to tangible soil threats. This situation is common across Pacific Island Countries and Territories (PICTs), where high throughput soil analysis laboratories are limited, and issues such as soil organic carbon decline, acidification and fertility declines are present. Soil spectral inference presents an opportunity in such regions to provide rapid insights into soil capital and condition, though the need for robust calibration libraries remains a limiting factor. This work investigates the utility of a regionally appropriate spectral library, the New Zealand Soil Spectral Library (NZSSL) to support the development of soil spectral inference in data-poor environments, such as PICTs, through a case study on the island of Tongatapu in The Kingdom of Tonga. We contrast the performance of existing partial least squares regression (PLSR) models developed for New Zealand soils on soils from Tongatapu and explore the opportunities for enhancement of predictions formed through memory-based learning (MBL) supplemented with local data. Our work shows the potential for cost-effective and timely soil monitoring through soil spectral inference in PICTs. The work further underscores the importance of regional cooperation and data-sharing for addressing soil security.

The Brazilian Soil Spectral Library data opening

Among the various repositories of soil spectral data, the Brazilian Soil Spectral Library (BSSL, https://bibliotecaespectral.wixsite.com/english), created and maintained by the GeoCiS research group, is representative of the pedodiversity of the region, since it combines soil spectra from agricultural and environmental research. The BSSL database contains 16,084 observations with soil-harmonized surface layer physicochemical and spectral data in the visible, near-infrared, short-wave infrared (Vis-NIR-SWIR, 350–2,500 nm) and mid-infrared (MIR, 4,000–600 cm-¹) ranges from all 26 Brazilian states and the Federal District. The idea of creating the BSSL was born in 1995, completed in 2019 and opened to users in 2023. This database is currently available online at https://zenodo.org/records/8361419. During oppening process, data filtering was performed to ensure reliable and valuable information provided to society. Then consistency and quality assessments were executed using Pearson's correlation and the Cubist algorithm in the R environment. Modeling analysis revealed the robust predictive power of the spectral database, facilitating the modeling of key soil attributes. An open-access BSSL will help researchers validate their results by comparing measured data with predicted data, enabling the development of new models or the improvement of existing ones. The BSSL is a globally significant spectral library due to its broad coverage and representation of different tropical soil classes. Soil spectral data can help governments and corporations by providing information to decision-makers regarding the conservation or exploitation of natural resources to monitor soil health.

Estimation of soil organic carbon in LUCAS soil database using Vis-NIR spectroscopy based on hybrid kernel Gaussian process regression

Soil Organic Carbon (SOC) is crucial for determining soil fertility and environmental quality. The problem with traditional SOC chemical analysis methods is that they are time-consuming and resource-intensive. In recent years, visible-near infrared (Vis-NIR) spectroscopy has been employed as an alternative method for SOC determination. However, when applied on a larger scale, the prediction accuracy of soil properties decreases due to the heterogeneity of samples. Therefore, this study compared and analyzed the performance of partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and gaussian process regression (GPR) in predicting SOC. On this basis, a GPR model based on a hybrid kernel function (HKF-GPR) was proposed for SOC prediction. This hybrid kernel function was designed according to the properties of single kernel functions and the characteristics of soil spectral data. Results indicate that in large soil spectral databases, the GPR model outperforms other models in estimating SOC. The HKF-GPR model achieved the best SOC estimation accuracy, with an R2 of 0.7671, RMSE of 5.2934 g/kg, RPD of 2.0721, and RPIQ of 2.5789. Compared to other regression models, the HKF-GPR model proposed in this paper offers broader applicability and superior performance, enabling SOC estimation in large soil spectral libraries.

Visible and infrared lab spectroscopy for soil texture classification: Analysis of entire spectra v/s reduced spectra

Soil, directly or indirectly, impacts seven of the Sustainable Development Goals set by the United Nations. Soil texture is a fundamental physical property that controls other properties ranging from soil stability, erodibility, compaction to water holding capacity, nutrient availability and fertility. While Visible Near-Infrared and Shortwave-Infrared (VNIR/SWIR) laboratory spectroscopy has been already used for soil texture classification, Mid Infrared (MIR) region and unison of the VNIR/SWIR and MIR region warrant quantification. Thus, the objectives of this work were: (1) to investigate the critical spectral regions for soil texture classification, (2) to compare the use of entire spectral bands v/s subset of spectral bands obtained via the feature selection method, and (3) to quantify the degree of misclassification in the neighbouring classes for a given textural class. This study utilized an ICRAF–ISRIC global soil spectral library consisting of 3643 VNIR/SWIR, MIR soil spectra and the USDA soil textural classes. Two classifiers were used for soil texture classification using the three databases (VNIR/SWIR, MIR, VNIR + MIR) with entire spectral bands and three databases with only the Partial Information Correlation (PIC) selected bands (VNIR/SWIR_PIC, MIR_PIC, VNIR + MIR_PIC). The mean confusion matrix, overall accuracy and kappa were calculated to evaluate classifiers' performances over 100 iterations. Two additional measures were proposed for partitioning inaccuracies between neighbouring and far classes: Correct-Neighbouring-Far classes distribution matrix and added neighbourhood accuracy. This work highlighted that: (1) the combined VNIR/SWIR + MIR region provided the best texture classification, followed by MIR and then VNIR/SWIR region, (2) the use of PIC selected bands provided lower classification performances when compared to using all bands but a massive reduction in the number of bands allowing to reduce model complexity, (3) the misclassifications were predominantly in the neighbouring classes rather than far classes, for a given texture class. Finally, the textural classes with poor classification performance had low areal and sample representation. These insights may launch a number of soil texture classification studies worldwide based on global soil spectral databases, further helping map soils and the associated ecosystem services it provides.

Subsetting reduces the error of MIR spectroscopy models for soil organic carbon prediction in the U.S. Great Plains

High demand for soil organic carbon data to support soil health and climate change mitigation efforts must be met with rapid, accurate, and inexpensive measurement methods. Mid-infrared spectroscopy shows promise as an alternative to conventional soil carbon analysis; however, its practicality depends on the construction and efficient use of soil spectral libraries. Subsetting, a calibration optimization technique, has potential to reduce model prediction errors. Nevertheless, the effectiveness of different subsetting criteria has yet to be well explored. This study assessed whether several subsetting criteria would result in calibration models with reduced error in the prediction of soil organic carbon content compared to models constructed from a full spectral dataset. A mid-infrared spectral library composed of Nebraska and Kansas soil samples was subset by (i) a nested wetland criterion, (ii) soilscapes, (iii) presence or absence of carbonates, and (iv) a combination of soilscape and carbonates. Partial least squares regression was used to construct all calibration models. Predictive performance of the subset models was compared to that of their corresponding full set model using several statistical metrics. Subsetting by wetlands reduced model error by 22 and 56 %. Subsetting by soilscape yielded a 13 to 55 % reduction in model error, while presence or absence of carbonates reduced model error by 21 and 46 %. Five of the eight combination soilscape and carbonate subset models reduced model error by 14 to 51 %. Overall, subsetting by soilscape or carbonate presence proved effective in improving model performance, with combination subsets proving beneficial under specific calibration set conditions.

Advanced Soil Organic Matter Prediction with a Regional Soil NIR Spectral Library Using Long Short-Term Memory–Convolutional Neural Networks: A Case Study

Soil analysis using near-infrared spectroscopy has shown great potential to be an alternative to traditional laboratory analysis, and there is continuously increasing interest in building large-scale soil spectral libraries (SSLs). However, due to issues such as high non-linearity in soil spectral data and complexity in soil spatial variation, the establishment of robust prediction models for soil spectral libraries remains a challenge. This study aimed to investigate the performance of deep learning algorithms, including long short-term memory (LSTM) and LSTM–convolutional neural networks (LSTM–CNN) integrated models, to predict the soil organic matter (SOM) of a provincial-scale SSL, and compare it to the normally used local weighted regression (LWR) model. The Hebei soil spectral library (HSSL) contains 425 topsoil samples (0–20 cm), of which every 3 soil samples were collected from dry land, irrigated land, and paddy fields, respectively, in different counties of Hebei Province, China. The results show that the accuracy of the validation dataset rank as follows: LSTM–CNN (R2p = 0.96, RMSEp = 1.66 g/kg) > LSTM (R2p = 0.83, RMSEp = 3.42 g/kg) > LWR (R2p = 0.82, RMSEp = 3.79 g/kg). The LSTM–CNN model performed the best, mainly due to its comprehensive ability to effectively extract spatial and temporal features. Meanwhile, the LSTM model achieved higher accuracy than the LWR model, owing to its built-in memory unit and its advantage of faster feature band extraction. Thus, it was suggested to use deep learning algorithms for SOM predictions in SSLs. However, their performance on larger-scale SSLs such as continental/global SSLs still needs to be further investigated.

In‐field soil spectroscopy in Vis–NIR range for fast and reliable soil analysis: A review

AbstractIn‐field soil spectroscopy represents a promising opportunity for fast soil analysis, allowing the prediction of several soil properties from one spectral reading representing one soil sample. This facilitates data acquisition from large amounts of samples through its rapidity and the absence of required chemical processing. This is of particular interest in agriculture, where the chance to retrieve information from soils directly in the field is very appealing. This review is focused on in‐field visible to near infrared (Vis–NIR) spectroscopy (350–2500 nm), aimed at analysing soils directly in the field through proximal sensing. The main scope was to explore the available knowledge to identify existing gaps limiting the reliability and robustness of in‐field measurement, to foster future research and help transition towards the practical application of this technology. For this purpose, a literature review was performed, and surveyed information encompassed sensor range, carrier platforms in use, sensor type, distance to the soil sample, measurement methodology, measured soil properties and soil management, among many others. From this, we derived a list of tools in use with their spectral measurement properties, including the potential cross‐calibration with soil spectral libraries from laboratory spectroscopy of soil samples and potential measured target soil properties. Different instruments and sensors used to measure at varying wavelength ranges and with different spectral qualities are available for a large range of prices. The most frequently analysed soil properties included soil carbon contents (soil organic carbon, soil organic matter, total carbon), texture (clay, silt, sand), total nitrogen, pH and cation exchange capacity. Future perspectives comprise the implementation of larger databases, including different instruments and cropping systems as well as methodologies combining existing knowledge regarding laboratory spectroscopy with in‐field methods. The authors highlight the need for a broadly accepted measurement protocol for in‐field soil spectroscopy, fostering harmonization and standardization and consequently a more robust application in practice.

Can we use a mid-infrared fine-ground soil spectral library to predict non-fine-ground spectra?

Mid-infrared (MIR) reflectance spectroscopy is a promising and rapid technology to accurately infer soil properties from a single scan. Fine-grinding is an expensive and time-consuming sample processing step in soil MIR spectroscopy that can have a major impact on spectral features and subsequent multivariate model calibrations. The use of existing fine-ground spectral libraries to predict soil properties of new samples (without fine-grinding) can reduce the cost and time in soil analysis. Calibration transfer studies between different grinding states of soil samples (using existing fine-ground spectral libraries to predict non-fine-ground spectra) are not available to the best of our knowledge. To address this research gap, this study investigated different calibration transfer and pre-processing techniques to link the MIR fine-ground spectral models and non-fine-ground soil spectra. Four calibration transfer techniques (direct standardization, external parameter orthogonalization, slope/bias correction, and spiking with extra weight) and four pre-processing techniques (first derivative, detrending, multiplicative signal correction, and standard normal variate) were investigated in this study. The United States Department of Agriculture National Soil Survey Center Kellogg Soil Survey Laboratory’s MIR spectral library (n > 72,000) and a randomly selected subset from the library (n = 519) were used as spectral datasets. Spiking (with extra weight) calibration transfer technique performed well for pH, clay, and sand when using the library (mean R2 = 0.70) and for organic carbon, cation exchange capacity, pH, clay, and sand when using the subset from the library (mean R2 = 0.66). Standard normal variate pre-processing technique performed well with organic carbon, cation exchange capacity, and sand when using the library (mean R2 = 0.67). Overall, spiking (with extra weight) enables the use of existing MIR fine-ground soil spectral libraries to predict those soil properties of new samples without fine-grinding, saving the cost and time.

Hyperspectral Imaging of Soil and Crop: A Review

The remote sensing is one of the precision technologies, can be used to monitor and assess the target area or object such as soil, crop, and water. Hyperspectral imaging (HSI), also known as imaging spectrometry or hyperspectral remote sensing, is a combined technique of spectroscopy and imaging system for sensing spectral information of an area or object. It involves capturing images of an object using multiple distinct optical bands that cover a wide range of the electromagnetic spectrum (350-2500 nm). The hyperspectral bands are continuous, narrow, and contagious and contain hundreds and thousands of numbers. Hyperspectral remote sensing is particularly valuable for gathering precise and up-to-date information necessary for agricultural planning and precision farming. HSI technology is the employment of hyperspectral sensors aids in analyzing soil physical (bulk density, texture, water content), chemical (pH, EC, SOC, and macro and micro nutrients), biological (SOM) properties and helps to categorize different crop varieties, identify pests and diseases, and assess crop yield and water stress in plants. The spectral reflectance of soil is affected by its properties such as mineral composition (Fe oxides), organic matter, soil moisture, and texture. For example, the spectral reflectance will be more if soil has less organic matter. The chemical bonds of soil molecules interact with the electromagnetic spectrum, and produce distinct pattern of reflectance. But the data collected from hyperspectral imaging are required big storage due to its large amount of data and finding the most appropriate hyperspectral image classification algorithm is a challenging task. So, these problems should be solved in future and national soil spectral library is needed for calibration of models which helps for efficient use of hyperspectral imaging technology.

Non-linear memory-based learning for predicting soil properties using a regional vis-NIR spectral library

Visible near-infrared (vis-NIR) spectroscopy has gained widespread recognition as an efficient and reliable approach for the rapid monitoring of soil properties. This technique relies on robust machine learning models that convert soil spectra information to soil properties. In particular, memory-based learning (MBL) has emerged as a powerful local modeling technique for soil spectral analysis. However, conventional MBL algorithms use linear models, disregarding the non-linear relationship between soil properties and vis-NIR spectra. Therefore, we hypothesize that non-linear memory-based learning (N-MBL) models can enhance prediction. This study develops and evaluates the N-MBL algorithm using the Lateritic Red soil spectral library (LRSSL) from Guangdong province in China. This library consists of 742 samples of vis-NIR spectra and corresponding soil properties, including pH, soil organic matter (SOM), total nitrogen (TN), total phosphorus (TP), and total potassium (TK). As a comparison, several commonly used supervised learning methods, such as Partial least squares regression (PLSR), Cubist, Random Forest (RF), Super vector machine (SVM), Convolution neural network (CNN), and local models (MBL), were compared to the proposed N-MBL. The results showed that local models generally outperformed supervised learning methods, particularly when applied to a large soil spectral library with a substantial number of samples (over 500). When comparing the two local models, MBL had more fluctuation of model performance compared to N-MBL as the number of selected nearest neighbors (k) varied between 30 and 250. As k increased, N-MBL showed higher R2 values for SOM and TN prediction than MBL but lower performance for pH and TK prediction. In addition, N-MBL outperformed MBL in predicting TP. In conclusion, N-MBL is a new local algorithm for predicting soil properties from vis-NIR spectra. It has a high potential to improve the accuracy of the prediction of multiple soil properties.

An interlaboratory comparison of mid-infrared spectra acquisition: Instruments and procedures matter

Diffuse reflectance spectroscopy has been extensively employed to deliver timely and cost-effective predictions of a number of soil properties. However, although several soil spectral laboratories have been established worldwide, the distinct characteristics of instruments and operations still hamper further integration and interoperability across mid-infrared (MIR) soil spectral libraries. In this study, we conducted a large-scale ring trial experiment to understand the lab-to-lab variability of multiple MIR instruments. By developing a systematic evaluation of different mathematical treatments with modeling algorithms, including regular preprocessing and spectral standardization, we quantified and evaluated instruments' dissimilarity and how this impacts internal and shared model performance. We found that all instruments delivered good predictions when calibrated internally using the same instruments' characteristics and standard operating procedures by solely relying on regular spectral preprocessing that accounts for light scattering and multiplicative/additive effects, e.g., using standard normal variate (SNV). When performing model transfer from a large public library (the USDA NSSC-KSSL MIR library) to secondary instruments, good performance was also achieved by regular preprocessing (e.g., SNV) if both instruments shared the same manufacturer. However, significant differences between the KSSL MIR library and contrasting ring trial instruments responses were evident and confirmed by a semi-unsupervised spectral clustering. For heavily contrasting setups, spectral standardization was necessary before transferring prediction models. Non-linear model types like Cubist and memory-based learning delivered more precise estimates because they seemed to be less sensitive to spectral variations than global partial least square regression. In summary, the results from this study can assist new laboratories in building spectroscopy capacity utilizing existing MIR spectral libraries and support the recent global efforts to make soil spectroscopy universally accessible with centralized or shared operating procedures.

A soil spectral library of New Zealand

Diffuse reflectance spectroscopy, both in the visible and near-infrared (vis-NIR: 350–2500 nm) and the mid-infrared (MIR: 2500–25,000 nm) ranges, has been increasingly employed as an alternative to obtaining a multitude of soil information and data non-destructively, rapidly, and cost-effectively. Soil spectral libraries (SSLs) have been developed across the world to calibrate prediction models for rapid and non-destructive assessment of soils at local, regional, national and global scales. Several continental or national libraries exist, for example, vis-NIR SSL in Europe, Australia, Czech Republic, Denmark, France, China and Brazil, and MIR SSL in the U.S., Switzerland and Brazil. In this study, we document the development of a vis-NIR and MIR SSL of New Zealand based on legacy and modern samples that have been sieved to 2 mm and air-dried, and explore the application of such libraries for predicting a wide range of soil properties, including soil carbon (total carbon or organic carbon), total nitrogen, pH, soil texture (sand, silt and clay), phosphate retention and available water capacity (field capacity and permanent wilting point). The vis-NIR and MIR spectral features were compared between New Zealand Soil Classification (NZSC) soil orders and the performances of both vis-NIR and MIR SSLs were compared with other national SSLs. Results of the study indicate that both vis-NIR and MIR SSL demonstrated reliable modelling performance using the PLSR model. However, MIR outperforms vis-NIR for all soil attributes. Furthermore, the study found that both vis-NIR and MIR have the potential to distinguish different soil orders within the NZSC.

Impact of Spectral Resolution and Signal-to-Noise Ratio in Vis–NIR Spectrometry on Soil Organic Matter Estimation

Recently, considerable efforts have been devoted to the estimation of soil properties using optical payloads mounted on drones or satellites. Nevertheless, many studies focus on diverse pretreatments and modeling techniques, while there continues to be a conspicuous absence of research examining the impact of parameters related to optical remote sensing payloads on predictive performance. The main aim of this study is to evaluate how the spectral resolution and signal-to-noise ratio (SNR) of spectrometers affect the precision of predictions for soil organic matter (SOM) content. For this purpose, the initial soil spectral library was partitioned into to two simulated soil spectral libraries, each of which were individually adjusted with respect to the spectral resolutions and SNR levels. To verify the consistency and generality of our results, we employed four multiple regression models to develop multivariate calibration models. Subsequently, in order to determine the minimum spectral resolution and SNR level without significantly affecting the prediction accuracy, we conducted ANOVA tests on the RMSE and R2 obtained from the independent validation dataset. Our results revealed that (i) the factors significantly affecting SOM prediction performance, in descending order of magnitude, were the SNR levels > spectral resolutions > estimation models, (ii) no substantial difference existed in predictive performance when the spectral resolution fell within 100 nm, and (iii) when the SNR levels exceeded 15%, altering them did not notably affect the SOM predictive performance. This study is expected to provide valuable insights for the design of future optical remote sensing payloads aimed at monitoring large-scale SOM dynamics.

Smartphone-based spectroscopy as a tool to estimate soil attributes for the citizen science concept

This study explores the potential of using smartphone cameras to estimate soil attributes as a field-based alternative to traditional sampling and lab analyses that are time-consuming, expensive, and non-friendly to the environment. It aims to investigate whether the color information captured by smartphone cameras could provide spectral information that can be utilized for soil attribute estimation using regression techniques. The DN values from smartphone camera photos were transformed into reflectance using colored plastic plated marker (PPM) reference panels. The spectral information of the PPM keys, obtained using a laboratory spectrometer, was convolved into 3 RGB smartphone bands. Using the legacy soil spectral library (SSL) of Israel on the 3-reflectance calibrated RGB smartphone bands, a good agreement with the reflectance of the laboratory spectrometer was obtained. The soil properties were modeled with the converted reflectance using the multiple linear regression (MLR), partial least square regression (PLSR), and ridge regression (RR) algorithms. The models created using the smartphone data (RGB and 6 synthetic bands) predicted six soil properties: i.e., soil organic matter (OM%), CaCO3, free iron oxides (Fe-dithionite), Al2O3, soil surface area (SSA), and hygroscopic moisture with the coefficient of determination (R2) values of 0.58, 0.54, 0.60, 0.55, 0.55 and 0.64, respectively. The quality of predictions was also evaluated using root mean square error (RMSE) and the ratio of prediction to interquartile distance (RPIQ). This research provides the results of an experiment to convert a personal smartphone camera to a spectrometer with the help of SSL. Despite the low spectral resolution of smartphone cameras, the models achieved fair results in predicting six soil properties. These findings could promote the adoption of citizen science methodologies for sustainable soil management as smartphone devices that are available to all can be simply calibrated to reflectance and used for proximal sensing of soils.

Leveraging large soil spectral libraries for sensor-agnostic field condition predictions of several agronomically important soil properties

Global pressures to improve soil organic carbon sequestration and soil health in general amongst the world’s agricultural soils are creating a demand for improved practice to drive positive and sustainable changes in the natural capital of soils. Incentive programs aimed to promote this must be informed by accurate observations of the state of soils, both temporally and spatially. Soil spectral inference is a useful method for capturing the state of soils cost-effectively, but the price of standard laboratory grade visible and near-infrared (Vis-NIR) sensors can limit its application. Further, the acquisition of spectra by these laboratory grade sensors is performed primarily in air-dried and ground condition, adding a time lag to information retrieval. Recently, low-cost, portable miniaturised near-infrafred (NIR) spectrometers have become available and have shown to be a viable alternative for the measurement of several agronomically important soil properties, which are also vital to the maintenance of soil health, including soil organic carbon (SOC), and cation exchange capacity (CEC). However, the implementation of new spectrometers, to new locations requires the creation of new spectral libraries, an expensive and labour-intensive process requiring large amounts of soil analytical and spectral data gathering. Thus, existing, laboratory grade Vis-NIR spectral libraries present a high-quality and high-resolution resource to leverage. This work demonstrates how existing spectral library resources can be accessed with cheaper, portable miniaturised NIR spectrometers with appropriate spectral filtering, and appropriate transformation matrices. In addition, the work shows that by correcting for the influences of spectral differences between soils scanned in field condition, and those prepared for analysis in the laboratory, greater uptake of spectral inference as a tool to evaluate the state of soils can be enabled. This work also demonstrates how large existing laboratory grade spectral libraries such as the CSIRO national Australian Vis-NIR soil spectral library can be queried and using memory-based learning or similar methods, such as RS-Local, and the most appropriate samples may be identified to be used for the prediction of soil properties. This work builds off an existing framework for the use of soil spectral inference for monitoring the state of soil, the Australian 2021 Soil Organic Carbon Credits Methodology Determination. Methods are demonstrated for the prediction of nine agronomically important soil properties, SOC, pH in water, pH in CaCl2, electrical conductivity, CEC, and exchangeable Ca, K, Mg and Na. For SOC a model using only 20 local samples was produced in this work with a Lin’s concordance correlation coefficient (LCCC) of 0.72, surpassing both the minimum requirement under the carbon credits methodology determination (LCCC 0.6), and a 50 sample local only model (LCCC 0.61). This example demonstrates that a significant further potential cost saving in laboratory analysis across soil monitoring projects can be achieved through selectively leveraging a large spectral library resource.