Soil Health Monitoring Research Articles

AI in Soil Health Monitoring: A Data-Driven Approach

Abstract: The sustainability of ecosystems and agricultural productivity depend on healthy soil. However, conventional techniques for evaluating soil health are sometimes time-consuming, labor-intensive, and restricted in their geographic reach. New opportunities for scalable, real-time soil health monitoring have been made possible by recent developments in artificial intelligence (AI) and data-driven methodologies. This study examines a thorough AI-powered system for tracking soil health, emphasizing methods for data collection, processing, and predictive modeling. AI models can provide precise forecasts of soil characteristics, health indicators, and possible crop yields by combining data from multiple sources, such as remote sensing, soil sensors, and historical data. This study offers a comprehensive analysis of recent AI applications in soil health monitoring and suggests a reliable, scalable approach intended to incorporate diverse data sources, guaranteeing precise and effective soil health assessment.

Al-driven Precision Agriculture: Advancing Crop Yield Prediction

This article explores the integration of Artificial Intelligence (AI) in precision agriculture, focusing on its role in advancing crop yield prediction and improving overall agricultural productivity. It examines three key areas: satellite imagery analysis, soil health monitoring, and weather data integration. The paper discusses how AI techniques such as Convolutional Neural Networks, IoT sensor networks, and ensemble methods are revolutionizing farming practices. It highlights the technical implementations of these technologies, their applications, and their significant impact on yield optimization, resource efficiency, and decision-making in agriculture. The study emphasizes the crucial role of AI in addressing global food security challenges and improving agricultural resilience to climate change.

Using MIR and XRF spectroscopy to develop a heavy metal leaching potential model in Irish top soils

The European Union aim to have all soils healthy by 2050. However, a major challenge to soil health monitoring is identifying key metrics for soil health indicators. Moreover, how to analyse numerous soil properties which are time-consuming, labour intensive and expensive. MIR spectroscopy is a rapid, non-destructive cheaper alternative to wet chemical methods. Here, we combined known soil properties that limit transport of heavy metals (i.e. drainage class, depth, organic matter, particle size/texture, bulk density and cation-exchange-capacity) to develop a topsoil (≤50 cm) leaching potential model (n = 3,515). The study area consisted of mostly grassland soils which had mainly high and moderately low leaching potential (43 and 36 %, respectively), with lower coverage of high and intermediate classes (10 and 11 %, respectively). However, known topsoil prediction models of 5–25 cm (n = 4759) were extrapolated to deeper samples 30–50 cm. As a result, 26 % of samples were identified as ‘out of control’ in peatland transition areas. For full spatial coverage for environmental modelling from spectral data, reference values are needed for the deeper samples in peatland transition areas.Furthermore, this study used a geological survey of the northern half of Ireland at ≤4 km2 resolution to map regions of naturally high levels of As, Cd, Cr, Cu, Ni and Pb by ICP and XRF spectroscopy. Geospatial clipping of heavy metal thresholds showed high coverage of As and Ni in Eastern regions, and Cd in the Midland regions of Ireland. Therefore, it would be useful to include fertiliser loadings, transport pathways or any source/recipient data to assess heavy metal movement throughout the soil profile, particularly in these regions.

Environmental variables improve the accuracy of remote sensing estimation of soil organic carbon content

Accurately and quickly estimating the soil organic carbon (SOC) content is crucial in the monitoring of global carbon. Environmental variables play a significant role in improving the accuracy of the SOC content estimation model. This study focuses on modeling methodologies and environmental variables, which significantly influence the SOC content estimation model. The modeling methods used in this research comprise multiple linear regression (MLR), partial least squares regression (PLSR), random forest, and support vector machines (SVM). The analyzed environmental variables include terrain, climate, soil, and vegetation cover factors. The original spectral reflectance (OSR) of Landsat 5 TM images and the spectral reflectivity after the derivative processing were combined with the above environmental variables to estimate SOC content. The results showed that: (1) The SOC content can be efficiently estimated using the OSR of Landsat 5 TM, however, the derived processing method cannot significantly improve the estimation accuracy. (2) Environmental variables can effectively improve the accuracy of SOC content estimation, with climate and soil factors producing the most significant improvements. (3) Machine learning modeling methods provide better estimation accuracy than MLR and PLSR, especially the SVM model which has the highest accuracy. According to our observations, the best estimation model in the study area was the “OSR + SVM” model (R2 = 0.9590, RMSE = 13.9887, MAE = 10.8075), which considered four environmental factors. This study highlights the significance of environmental variables in monitoring SOC content, offering insights for more precise future SOC assessments. It also provides crucial data support for soil health monitoring and sustainable agricultural development in the study area.

Developing a robust soil health indicator selection framework

Developing a robust soil health indicator selection framework The EU Soil Health Monitoring Law proposes twelve main soil indicators for reporting soil health. There is a need to ensure that these indicators and other subsequent measures are robust for their purpose. Since there is no single indicator for soil health, a robust framework for selecting indicators using agreed-upon criteria is needed(1,2). A summary of the selection framework criteria is discussed below and summarized in Figure 1. This framework is based on synthesizing accepted and tested methods to assess current indicators and provide a basis for selecting new ones in the future. Selected indicators will be dependent on their ability to assess soil ecosystem functions and services(3).

Smart Solutions for Sustainable Agriculture: Design and Development of IoT-Powered Soil Health Identification Systems

This research examines smart solutions for agricultural sustainability using IoT-powered soil health detection systems. Innovative solutions are needed to manage resources and protect the environment as the world population grows and agricultural resources are under strain. IoT-enabled soil health monitoring has great potential. The suggested system uses IoT sensors to measure soil moisture, pH, nutrient content, and temperature in real time. This data is analyzed using powerful data analytics and machine learning algorithms to provide farmers soil health information. Monitoring soil quality allows farmers to make educated irrigation, fertilization, and crop selection choices, optimizing resource use and yields while minimizing environmental effect. The study also examines sensor selection, data transmission methods, and data security for IoT-powered soil health detection systems. Widespread use of these technologies might boost agricultural output, lower input costs, and enhance food security. Finally, IoT-powered soil health detection systems are a major step toward agricultural sustainability. These devices enable precision farming that is ecologically friendly and profitable by giving real-time soil data. However, effective implementation would need agricultural value chain stakeholders to collaborate and continued research to address growing issues and possibilities.

Assessing soil functioning: What is the added value of soil organic carbon quality measurements alongside total organic carbon content?

Soil organic carbon (SOC) content is the most widely used soil health indicator, but many soil functions are also influenced by the quality of SOC. Yet, standardized SOC quality parameters that can be used in soil health assessments in addition to SOC content are still in development. Here, we investigated the relationships between various SOC parameters (both quantity and quality) and soil functions.We collected 223 soil samples from arable fields in two contrasting Dutch soil types i.e., marine clay and sand. For each sample, we assessed three soil functions (i.e., biological population regulation, element cycling, and soil structure and water regulation) by measuring five indicators per function. We also analyzed SOC quality with four techniques (C:N-ratio, POX-C, Rock-Eval, POM-MAOM fractionation), resulting in 21 SOC quality parameters, and measured SOC content. We then determined for each soil type how much variation in each function indicator was explained by the SOC parameters and other measured intrinsic soil properties.We found that SOC parameters and intrinsic soil properties explained at most 30 ± 22% of the variation in soil function indicators. SOC content explained 9 ± 16% of the variation across functions and soil types. Including one single SOC quality parameter alongside SOC content never had significant added value in explaining soil functions. Only including multiple Rock-Eval parameters alongside SOC content significantly increased the explained variation compared to SOC content alone, as well as combining multiple parameters from the four different SOC quality techniques.We conclude that the relationships between the SOC quality parameters and soil functions are insufficiently straight-forward to add significant explanatory power to SOC content alone. We recommend that before including SOC quality parameters in soil health monitoring, more emphasis should be put on evaluating their relation to soil functions and their potential redundancy when used alongside SOC content.

Revolutionizing Agriculture with Nanotechnology: Advances, Applications, and Sustainability Considerations

The integration of nanotechnology into agriculture has garnered significant interest due to its potential to revolutionize agricultural practices. This paper explores the application of nanotechnology in crop protection, nutrient delivery, soil management, and environmental sustainability. Nanopesticides and nanofertilizers represent notable advancements, offering enhanced efficacy, reduced environmental impact, and improved targeted delivery of active ingredients. Nanomaterials such as nanoparticles and nanocapsules encapsulate nutrients and agrochemicals, ensuring gradual release and optimized plant uptake. Nanosensors, based on materials like carbon nanotubes and quantum dots, enable real-time monitoring of soil health, crop growth, and environmental conditions, facilitating precision agriculture. Nanomaterials also play a role in soil remediation and pollution control by degrading pollutants and enhancing soil fertility. Additionally, nanobiotechnology offers eco-friendly solutions for pest and disease management through nanoscale delivery systems for biocontrol agents and plant vaccines. Despite the transformative potential of nanotechnology in agriculture, considerations of safety, regulatory oversight, and ethical implications are essential. Interdisciplinary collaboration and stakeholder engagement will be crucial to harness the full benefits of nanotechnology for sustainable agriculture.

Counterion selection for ion controls of CuO-nanoparticles is important for assessing soil biological responses

Environmental evaluations of metal nanoparticles (NP) rely on seperating the effects of the metal NP from its dissolution products. However, the coordinating or counter anion used in experimental controls may potentially influence biotic indicators used in ecotoxicology and soil health monitoring, thereby compromising the ability to detect real nanoparticle effects and potentially confounding interpretation of metal-NP impacts. Using the example of copper oxide (CuO) NP, we demonstrate for the first time that depending on the anion used in the metal ion control (CuCl2 versus CuSO4), different and even opposite conclusions may be drawn for CuO-NP effects. This include a key biological indicator such as enzyme activity in soil samples. Moreover, this effect was specific to environmental conditions and indicator type, raising important methodological and interpretive implications to assess the CuO-NP impacts on soils. Our findings imply that assessments of soil health impacts of metal-NP should consider multiple coordinating anion controls for a given metal, especially when the counterion is known to impact the biological indicator including nutrient ions.

Efficient Soil Health Monitoring and Irrigation Management System Using Fuzzy Logic

Abstract: The need for sustainable agriculture is acutely felt due to ever increasing global water crisis. Efficient irrigation management is crucial in this regard. The proposed system employs a network of soil moisture sensor distributed over a agricultural field, where continuous acquisition of real time data on soil moisture levels is done. Soil moisture measurement is a vital parameter in terms of precision agriculture, which affects the irrigation scheduling for ensuring optimal crop growth. Traditional methods related face challenges adapting to changing soil patterns at different conditions. The system proposes application of fuzzy logic algorithm for processing of data. Key advantages of using fuzzy logic in soil moisture measurement include improved precision in moisture detection, enhanced ability to make more informed irrigation decisions. The proposed system delivers a model for promoting water conservation, enhancing crop productivity and maintaining soil health.

The Western Greece Soil Information System (WΕSIS)—A Soil Health Design Supported by the Internet of Things, Soil Databases, and Artificial Intelligence Technologies in Western Greece

Soil quality is vital for ecosystem stability, impacting human, plant, and animal health. Traditional soil quality assessments are labor-intensive and costly, making them unsuitable for smart agriculture. To overcome this, Internet of Things (IoT) and artificial intelligence (AI) technologies are employed for sustainable agriculture, enabling real-time data collection and analysis, trend identification, and soil health optimization. The Western Greece Soil Information System (WΕSIS) offers open-access data and services for soil health and sustainability. It includes modules for soil quality indicators, sustainable fertilization management zones, soil property distribution, prediction, mapping, statistical analysis, water management, land use maps, digital soil mapping, and crop health calculation. Integrating the IoT and AI allows for real-time and remote monitoring of soil conditions, managing soil interventions adaptively and in a data-driven way, enhancing soil resources’ efficiency and sustainability, and increasing crop yield and quality. AI algorithms assist farmers and regional stakeholders in optimizing production lines, methodologies, and field practices, reducing costs and increasing profitability. This promotes a circular economy, a soil- and climate-resilient future, biodiversity protection targets, and enhanced soil fertility and productivity. The proposed IoT/AI technical architecture can underpin the development of soil health monitoring platforms, integrating data from various sources, automating data collection, and providing decision support tools.

Nanotechnology-based Sensors for Real-time Monitoring and Assessment of Soil Health and Quality: A Review

Soil health and quality are critical factors in maintaining sustainable agriculture, ecosystem stability, and global food security. Conventional methods for assessing soil properties are often time-consuming, labor-intensive, and lack real-time monitoring capabilities. Nanotechnology has emerged as a promising approach to develop advanced sensors for rapid, in-situ, and continuous monitoring of soil health parameters. This comprehensive review discusses the recent advancements in nanotechnology-based sensors for soil health assessment, their working principles, applications, challenges, and future prospects. We highlight the potential of various nanomaterials, such as carbon nanotubes, graphene, metal oxide nanoparticles, and quantum dots, in fabricating highly sensitive, selective, and robust soil sensors. The integration of these nanosensors with wireless communication technologies and data analytics enables real-time monitoring and precision agriculture practices. Furthermore, we discuss the environmental and ecological implications of deploying nanosensors in soil and the need for standardized protocols and regulations. This review provides valuable insights into the current state-of-the-art and future directions of nanotechnology-based sensors for soil health monitoring, promoting sustainable agriculture and environmental management.

Temporal monitoring of free-living nematode communities for evaluation of soil health in an arable crop rotation

There is a growing interest in finding reliable methods for monitoring soil health using bioindicators. Free-living nematodes are an ideal indicator group because of their rapid response to changes in soil conditions. This UK study aims to assess their efficacy as bioindicators using two field experiments. In Experiment-1, the treatments included Farmyard Manure, Green Manure consisting of a mix of Raphanus sativus and Vicia sp., and Standard Practice serving as the control receiving N-fertiliser only. The same treatments, except Farmyard Manure, were compared in Experiment-2, which was on a sloping site with a different textured soil. Soil samples were collected twice during each crop season, in Spring and Autumn, for Experiment-1, and only in Autumn for Experiment-2. Ecological indices that categorise nematodes by feeding preference using morphological differences and life strategies (i.e. functional guilds) were calculated. Indices were compared with the abundance of nematode trophic groups to evaluate their use as soil indicators for understanding crop management practices and their legacy effects. Results showed that identification to trophic groups alone was not a sufficiently sensitive approach for assessing changes in the selected management practices. The variations among trophic groups and treatments within the same sampling period were significantly different for bacterivores, fungivores, predators, omnivores, and herbivores. These differences did not always cooccur within the same sampling period, with bacterivores and plant-parasites of economic importance showing greater responses. The food web analyses, calculated by applying the Enrichment Index and Structure Index, and Plant Parasite Index, provided a more sensitive indicator and allowed more effective diachronic monitoring. While using the composition of trophic groups appears to be an attractive solution, their application is best linked to quantifying short-term changes in soil condition and were not as well suited to longer-term soil health monitoring.

Empowering coffee farming using counterfactual recommendation based RNN driven IoT integrated soil quality command system

Soil health is essential for whirling stale soil into rich coffee-growing land. By keeping healthy soil, coffee producers may improve plant growth, leaf health, buds, cherry and bean quality, and yield. Traditional soil monitoring is tedious, time-consuming, and error-prone. Enhancing the monitoring system using AI-based IoT technologies for quick and precise changes. Integrated soil fertility control system to optimize soil health, maximize efficiency, promote sustainability, and prevent crop threads using real-time data analysis to turn infertile land into fertile land. The RNN-IoT approach uses IoT sensors in the coffee plantation to collect real-time data on soil temperature, moisture, pH, nutrient levels, weather, CO2 levels, EC, TDS, and historical data. Data transmission using a wireless cloud platform. Testing and training using recurrent neural networks (RNNs) and gated recurrent units gathered data for predicting soil conditions and crop hazards. Researchers are carrying out detailed qualitative testing to evaluate the proposed RNN-IoT approach. Utilize counterfactual recommendations for developing alternative strategies for irrigation, fertilization, fertilizer regulation, and crop management, taking into account the existing soil conditions, forecasts, and historical data. The accuracy is evaluated by comparing it to other deep learning algorithms. The utilization of the RNN-IoT methodology for soil health monitoring enhances both efficiency and accuracy in comparison to conventional soil monitoring methods. Minimized the ecological impact by minimizing water and fertilizer utilization. Enhanced farmer decision-making and data accessibility with a mobile application that provides real-time data, AI-generated suggestions, and the ability to detect possible crop hazards for swift action.

Revolutionizing agriculture: Unleashing the potential of AI and big data in soil health monitoring

Revolutionizing agriculture: Unleashing the potential of AI and big data in soil health monitoring In a recent interview, our editors delved into the world of soil health monitoring and the transformative role played by artificial intelligence (AI), big data, and machine learning, with Mogens H. Greve, Professor and Head of the Soil Section at the Institute of Agroecology, Aarhus University. Professor Mogens H. Greve, provided valuable insights into the evolving landscape of soil science and its intersection with cutting-edge technologies in this exclusive interview with Open Access Government. The integration of soil mapping and AI Greve, an experienced soil mapping expert, has reshaped the conventional viewpoint by underscoring the pivotal role of soil mapping within the realm of AI for soil health.

Health and Characteristics of Australian Apple Growing Soils

Despite being the highest value fruit crop in Australia, little is known about the types and condition or “health” of Australia’s apple growing soils. This study is unique in being the first to report the condition and characteristics of Australia’s apple growing soils; it provides essential baseline data for future monitoring of soil health in apple production systems, as well as soil physical and chemical data required for the development of perennial soil-tree-climate models. Soil chemical and physical properties were measured at 34 orchards, across five states. Soils were assessed for water retention, hydraulic conductivity, bulk density, macroporosity, organic carbon, CEC, ESP, pH, and EC. Despite high to very high levels of organic carbon, most topsoils were moderately to poorly structured. Around one-third to half of all sites showed evidence of poor aeration or impeded drainage, whilst 10 of the 34 sites were prone to nutrient leaching. Plant available soil water (PAWC) varied greatly between sites from 31 mm to 170 mm from 0 to 60 cm depth and between sites within the same soil order. Whilst topsoils had high to very high levels of organic carbon (average: 2.46%), they were otherwise poorly structured, with higher than expected bulk density (average: 1.32 g/cm3) and lower than expected air capacity (average: 9.97%) and macroporosity (average: 1.75%). Subsoils were also found to have little soil water availability (average: 15.39 mm/100 mm), low air capacity (average: 5.28%), and low CEC (average: 8.12 cmol (+) kg−1). Notably, 10 of the 34 sites had less than 6 cmol (+) kg−1 CEC throughout the entire soil profile, indicating potential risk of nutrient leaching. This study indicates that apple growing soils require careful management to improve topsoil structure, and to maintain or increase soil carbon, as well as use of soil moisture sensors to schedule irrigation. In addition, some sites also require improved subsoil drainage and care to ensure fertigation and irrigation do not result in leaching of nutrients beneath the root zone.

Urban Agriculture & Regional Food Systems Special Section: Improving Livability in Urban Areas: Examining Urban and Peri‐Urban Soil and Plant Management

AbstractAs urban agriculture increasingly becomes part of our regional food systems, its role in sustainable urban development grows. Urban agriculture can sustain food demand and contribute to food security, environmental sustainability, and community health. However, soil‐related factors in urban agricultural systems pose unique challenges not found in more rural environments, and issues such as soil fertility, soil biodiversity, soil contamination, and existing policy demand further investigation to deepen and enhance the potential contribution of urban agriculture to livability in urban areas. This special issue collects studies to support the need for sustainable soil management, crop diversification, and management strategies for optimal soil health and good crop yield and quality. In addition, the issue examines recent advances in remote sensing technologies and deep learning techniques that offer potential tools for soil health monitoring and plant disease detection related to existing plant‐based contamination, providing a way forward to make informed decisions for policy stakeholders and land planners. Combining these initiatives into urban planning and public health policies could have a considerable impact on urban well‐being and resilience.

IoT Integration for Enhanced Turmeric Cultivation: A Case Study in Smart Agriculture

The agricultural sector serves as a fundamental cornerstone of the economies of numerous countries, necessitating technological advancements despite limited financial resources. The Internet of Things (IoT) presents a novel aspect within the field of soil health monitoring, which has significant implications for advancing smart agriculture and farming practices. Integrating conventional agricultural practices with cutting-edge technologies, such as the IoT and Wireless Sensor Networks (WSN), can foster Smart Agriculture (SA). This paper presents IoT Integration for Enhanced Turmeric Cultivation (IoT-ETmC) in the context of SA. The TurmFox IoT and Edge-to-Cloud (ETC) technology can analyze gathered data and send it to the user through internet connectivity. The work involves the implementation of TurmFox in experiments focused on turmeric cultivation. The results demonstrate a notable improvement in the quality of turmeric as a direct outcome of this intervention. The curcumin levels in the given product are notably higher, ranging from 4450 to 5450 mg per 120g. This paper also aims to demonstrate the intuitive configuration of sensor-to-actuator connections for implementing desired SA. The real-time data obtained from Turmfox provides information on the pH values, moisture levels, and temperature, allowing for observing dynamic variations in environmental conditions within the specified period. The pH level was 6.5 at 09:00, with a moisture content of 51 g/m3 and a temperature of 293 K.

A Simple, Affordable, Do-It-Yourself Method for Measuring Soil Maximum Water Holding Capacity

ABSTRACT There is an increasing need for accessible methods to monitor soil health. Our primary objective was to evaluate an accessible, do-it-yourself method for measuring the maximum water holding capacity – we call this the funnel, filter paper, and drainage (MWHCFFPD) method. First, we compared MWHCFFPD to the water desorption method via pressure cells (WHCPC), routinely used for generating soil water retention curves, using 10 soils from a wide range of textures (4–55% clay). Second, we tested the sensitivity of the MWHCFFPD to methodological variations likely encountered by citizen scientists. The two methods were quite comparable in precision, with mean coefficient of variances of 3.5% and 4.4% for the FFPD and water desorption method, respectively. The MWHCFFPD and WHCPC methods were comparable, with MWHCFFPD best correlating to WHCPC at −2.45 kPa (R2 = 0.98). The MWHCFFPD method is somewhat sensitive to some methodological modifications, most notably variation in water source, but with standardized protocols could be scientifically robust. Overall, MWHCFFPD can be used as a simple and affordable test of sieved soil structure and organic matter, and thus has potential to expand soil health monitoring.

Electrochemical Framework for Dynamic Tracking of Soil Organic Matter (SOM)

Soil Health parameters serve as excellent surrogate measures towards assessing environmental quality and understanding effects of climate change mitigation via carbon sequestration. Soil health monitoring in the near past has been highly qualitative and speculative with more recent advancements still trying to fill the void of determining a holistic soil profile through phantom based measurements. In fields and crop-circles, testing methods to perform in-situ profiling however from one lab is likely to vary with another and hence results are not universally compatible. Additionally, these normalized techniques ideally involve empirical approaches, extensive sample preparation which adds on to a temporal factor along with equipment for extraction and subsequently-analysis. Even with the upcoming research breakthroughs in non-destructive approaches like spectroscopy and tomography-based models, there is a barrier in-terms of equipment complexity and availability as well as high costs and high logistical overhead.There are a wide number of redox systems present in soil that exist in reduced state under ideal conditions (submerged). While Carbon monitoring would be highly beneficial in the field, an overall sense of the organic matter nutrients present in soil denoted as soil organic matter understanding would offer a wholistic manner of surveying soil and environmental health. In this work, faradaic and non-faradaic measurements are utilized to determine threshold changes in soil electrochemical activity due to presence of various electroactive substances present in the matrix. First, a galvanostatic approach using the chronopotentiometry modality was applied to a soil slurry system- ‘test’ sample to which different levels (w/v %) of the following amendments were added to see how the effective charge modulation can be visualized. Utilizing this experimental framework as preliminary information- A hypothesized mechanism of interaction between the RTIL (Room Temperature Ionic-Liquid) modified electrode and the OM functional moieties based on hydrogen bonding and pi-pi interactions captured using charge-based (chronocoulometry) and interfacial mapping-based (electrochemical impedance spectroscopy) method is utilized to design and test a first-of-a-kind electrochemical soil organic matter (SOM) sensor. Figure 1. Chronopotentiometric characterization of soil organic matter using an RTIL modified electrode. Figure 1