Search

The aim of this study was to narrow the research gap of ambiguity in which machine learning algorithms should be selected for evaluation in digital soil organic carbon (SOC) mapping. This was performed by providing a comprehensive assessment of prediction accuracy for 15 frequently used machine learning algorithms in digital SOC mapping based on studies indexed in the Web of Science Core Collection (WoSCC), providing a basis for algorithm selection in future studies. Two study areas, including mainland France and the Czech Republic, were used in the study based on 2514 and 400 soil samples from the LUCAS 2018 dataset. Random Forest was first ranked for France (mainland) and then ranked for the Czech Republic regarding prediction accuracy; the coefficients of determination were 0.411 and 0.249, respectively, which was in accordance with its dominant appearance in previous studies indexed in the WoSCC. Additionally, the K-Nearest Neighbors and Gradient Boosting Machine regression algorithms indicated, relative to their frequency in studies indexed in the WoSCC, that they are underrated and should be more frequently considered in future digital SOC studies. Future studies should consider study areas not strictly related to human-made administrative borders, as well as more interpretable machine learning and ensemble machine learning approaches. [ABSTRACT FROM AUTHOR]

In this paper, some of the basic information on Ground-Penetrating Radar (GPR), its applications (especially in the field of civil engineering) and limitations are presented. As a non-destructive technique, GPR is a powerful tool for the investigation of structures and structural members, roads, geological layers, archaeological sites and many more. The technology is based on electromagnetic radiation in the UHF/VHF range (10 MHz to 3 GHz). The choice of the frequency depends on the intended use, depth and size of the target and medium where the target is located. Joined with other testing methods (ultrasound method, dynamic methods with forced or ambient vibrations, electrical conductivity testing, etc.), GPR can provide a deep insight into the investigated object. However, like many other non-destructive methods, the choice of input parameters may affect the results. In this regard, a case study presented in this paper demonstrates not only different applications of GPR in civil engineering but also the determination (calibration) of one of those input parameters: the dielectric constant of glued laminated timber. The challenge here was not only to investigate the influence of the direction of measurements with regards to the direction of the fibers but also to acknowledge the contribution of the test antenna used during testing and dielectric constant calibration. [ABSTRACT FROM AUTHOR]

Considering the demand for the optimization of the technical factors of spraying for a greater area coverage and minimal drift, field tests were carried out to determine the interaction between the area coverage, number of droplets per cm2, droplet diameter, and drift. The studies were conducted with two different types of sprayers (axial and radial fan) in an apple orchard and a vineyard. The technical factors of the spraying interactions were nozzle type (ISO code 015, code 02, and code 03), working speed (6 and 8 km h−1), and spraying norm (250–400 L h−1). The airflow of both sprayers was adjusted to the plantation leaf mass and the working pressure was set for each repetition separately. A method using water-sensitive paper and a digital image analysis was used to collect data on coverage factors. The data from the field research were processed using four machine learning models: quantile random forest (QRF), support vector regression with radial basis function kernel (SVR), Bayesian Regularization for Feed-Forward Neural Networks (BRNN), and Ensemble Machine Learning (ENS). Nozzle type had the highest predictive value for the properties of number of droplets per cm2 (axial = 69.1%; radial = 66.0%), droplet diameter (axial = 30.6%; radial = 38.2%), and area coverage (axial = 24.6%; radial = 34.8%). Spraying norm had the greatest predictive value for area coverage (axial = 43.3%; radial = 26.9%) and drift (axial = 72.4%; radial = 62.3%). Greater coverage of the treated area and a greater number of droplets were achieved with the radial sprayer, as well as less drift. The accuracy of the machine learning model for the prediction of the treated surface showed a satisfactory accuracy for most properties (R2 = 0.694–0.984), except for the estimation of the droplet diameter for an axial sprayer (R2 = 0.437–0.503). [ABSTRACT FROM AUTHOR]

As conservation tillage becomes one of the foundations of sustainable crop production, important questions arise about its value, which needs to be defined and evaluated. One of the most important indicators of soil compaction is penetration resistance (PR), which comes as a short-term response to the state of soil physics. The objective of this work is to compare different tillage treatments (TT) on soil compaction on silty clay loam Stagnosol and silt Gleysol in the continental part of Croatia. The research included three tillage treatments: ST—conventional tillage, CTD—deep conservation tillage, and CTS—shallow conservation tillage. PR was determined on each soil depth of 5 cm up to 80 cm, and measuring was provided on two measuring dates. The obtained results showed a higher influence of the year factor than TT. In the upper layers (up to 35 cm), PR values between TT were with significant differences, but in most cases below root-limiting critical values, while in deeper soil layers (35–80 cm), we found that penetration values on each tillage treatment begin to stabilize and smooth out in most cases, with similar dynamics on both soil types and measurement dates. In most of the cases, the highest PR was measured for conservation treatments in wetter soil conditions. [ABSTRACT FROM AUTHOR]

This review focuses on digital soil organic carbon (SOC) mapping at regional or national scales in spatial resolutions up to 1 km using open data remote sensing sources, emphasizing its importance in achieving United Nations' Sustainable Development Goals (SDGs) related to hunger, climate action, and land conservation. The literature review was performed according to scientific studies indexed in the Web of Science Core Collection database since 2000. The analysis reveals a steady rise in total digital soil mapping studies since 2000, with digital SOC mapping studies accounting for over 20% of these studies in 2023, among which SDGs 2 (Zero Hunger) and 13 (Climate Action) were the most represented. Notably, countries like the United States, China, Germany, and Iran lead in digital SOC mapping research. The shift towards machine and deep learning methods in digital SOC mapping has surged post-2010, necessitating environmental covariates like topography, climate, and spectral data, which are cornerstones of machine and deep learning prediction methods. It was noted that the available climate data primarily restrict the spatial resolution of digital SOC mapping to 1 km, which typically requires downscaling to harmonize with topography (up to 30 m) and multispectral data (up to 10–30 m). Future directions include the integration of diverse remote sensing data sources, the development of advanced algorithms leveraging machine learning, and the utilization of high-resolution remote sensing for more precise SOC mapping. [ABSTRACT FROM AUTHOR]

The paper presents research on measuring and the possibility of prediction of noise levels on the left and right sides of the operator within the cabin of an agricultural tractor when moving across various agrotechnical surfaces, considering movement velocity and tire pressures while employing machine learning techniques. Noise level measurements were conducted on a LANDINI POWERFARM 100 type tractor, and aligned with standards (HRN ISO 5008, HRN ISO 6396 and HRN ISO 5131). The obtained noise values were divided into two data sets (left and right set) and processed using multiple linear regression (mlr) and three machine learning methods (gradient boosting machine (gbm); support vector machine using radial basis function kernel (svmRadial); monotone multi-layer perceptron neural network (monmlp)). The most accurate method, considering surfaces, from the left side data set—(R2 0.515–0.955); (RMSE 0.302–0.704); (MAE 0.225–0.488)—and the right side—(R2 0.555–0.955); (RMSE 0.180–0.969); (MAE 0.139–0.644)—was monmlp predominantly, and to a lesser extent svmRadial. On analyzing the total data sets from the left and right sides regarding surfaces, gbm emerged as the most accurate method. The application of machine learning methods demonstrated data accuracy, yet in future research, measurements on certain surfaces may need to be repeated multiple times potentially to improve accuracy further. [ABSTRACT FROM AUTHOR]

Due to the projected increase in food production by 70% in 2050, crops should be additionally protected from diseases and pests to ensure a sufficient food supply. Transfer deep learning approaches provide a more efficient solution than traditional methods, which are labor-intensive and struggle to effectively monitor large areas, leading to delayed disease detection. This study proposed a versatile module based on the Inception module, Mish activation function, and Batch normalization (IncMB) as a part of deep neural networks. A convolutional neural network (CNN) with transfer learning was used as the base for evaluated approaches for tomato disease detection: (1) CNNs, (2) CNNs with a support vector machine (SVM), and (3) CNNs with the proposed IncMB module. In the experiment, the public dataset PlantVillage was used, containing images of six different tomato leaf diseases. The best results were achieved by the pre-trained InceptionV3 network, which contains an IncMB module with an accuracy of 97.78%. In three out of four cases, the highest accuracy was achieved by networks containing the proposed IncMB module in comparison to evaluated CNNs. The proposed IncMB module represented an improvement in the early detection of plant diseases, providing a basis for timely leaf disease detection. [ABSTRACT FROM AUTHOR]

The research on lignocellulose pretreatments is generally performed through experiments that require substantial resources, are often time-consuming and are not always environmentally friendly. Therefore, researchers are developing computational methods which can minimize experimental procedures and save money. In this research, three machine learning methods, including Random Forest (RF), Extreme Gradient Boosting (XGB) and Support Vector Machine (SVM), as well as their ensembles were evaluated to predict acid-insoluble detergent lignin (AIDL) content in lignocellulose biomass. Three different types of harvest residue (maize stover, soybean straw and sunflower stalk) were first pretreated in a laboratory oven with hot air under two different temperatures (121 and 175 °C) at different duration (30 and 90 min) with the aim of disintegration of the lignocellulosic structure, i.e., delignification. Based on the leave-one-out cross-validation, the XGB resulted in the highest accuracy for all individual harvest residues, achieving the coefficient of determination (R2) in the range of 0.756–0.980. The relative variable importances for all individual harvest residues strongly suggested the dominant impact of pretreatment temperature in comparison to its duration. These findings proved the effectiveness of machine learning prediction in the optimization of lignocellulose pretreatment, leading to a more efficient lignin destabilization approach. [ABSTRACT FROM AUTHOR]

Leaf Soil-Plant Analysis Development (SPAD) prediction is a crucial measure of plant health and is essential for optimizing indoor plant management. The deep learning methods offer advanced tools for precise evaluations but their adaptation to the heterogeneous indoor plant ecosystem presents distinct challenges. This study assesses how accurately deep neural network (DNN) predicts SPAD values in leaves on indoor plants when compared to well-established machine learning techniques, including Random Forest (RF) and Extreme Gradient Boosting (XGB). The covariates for prediction were based on low-cost multispectral and soil electro-conductivity (EC) sensors, enabling a non-destructive sensing approach. The study also strongly emphasized multicollinearity analysis quantified by the Variance Inflation Factor (VIF) and two independent indices, as well as its effect on prediction accuracy using deep and machine learning methods. DNN resulted in higher accuracy to RF and XGB, also performing better using filtered data after multicollinearity analysis based on the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) (R2 = 0.589, RMSE = 11.68, MAE = 9.52) in comparison to using all input covariates (R2 = 0.476, RMSE = 12.90, MAE = 10.94). Overall, DNN was proven as a more accurate prediction method than the conventional machine learning approach for the prediction of leaf SPAD values in indoor plants, despite using heterogenous plant types and input covariates. [ABSTRACT FROM AUTHOR]

The occurrence of late spring frosts due to climate change causes great damage to plantation production worldwide. The main objective of the paper is to provide a comprehensive overview of the problem and to outline effective protective measures against late spring frosts. The nature of frost depends on regional, altitudinal, and geographic differences, but they all share a common problem: they remove heat, resulting in the freezing of new plant growth and flowers. Tissue freezing is affected by critical temperatures and the frost type, intensity, and duration. Protection against late spring frosts can be broadly divided into three categories: active, passive, and chemical measures. In the field of agricultural engineering, various techniques have been thoroughly researched, and their effectiveness has been confirmed by research. These include various sprinkler systems, different heating devices, and large-diameter fans. Conclusive findings are being made on the performance of these systems in sub-zero temperatures and their cost-effectiveness. Climate change increases the importance of protecting permanent crops from late spring frosts and requires advances in agricultural technology to meet changing production demands and challenges. [ABSTRACT FROM AUTHOR]

Infiltration models and impervious surface models have gained significant attention in recent years as crucial tools in urban and environmental planning, to assess the extent of land-surface changes and their impacts on hydrological processes. These models are important for understanding the hydrological dynamics and ecological impacts of urbanization and for the improvement of sustainable land-use planning and stormwater-management strategies. Due to the fact that many authors partially or entirely overlook the significance of the infiltration process in geographic information system (GIS) analyses, there is currently no universally accepted method for creating an infiltration model that is suitable for GIS multicriteria decision analysis (GIS-MCDA). This research paper presents an innovative approach to modeling the infiltration-efficiency index (IEI) for GIS analysis, with a focus on achieving high-quality results. The proposed methodology integrates very-high-resolution (VHR) remote-sensing data, GIS-MCDA, and statistical methods. The methodology was tested and demonstrated on a small sub-catchment in Metković, Croatia. The study developed a VHR IEI model from six specific criteria that produced values between 0 and 0.71. The model revealed that 14.89% of the research area is covered by impervious surfaces. This percentage is relatively favorable when compared to urban areas globally. The majority of the research area (62.79%) has good infiltration efficiency. These areas are predominantly characterized by agricultural land use, encompassing orchards, tangerines, olive groves, vineyards, and a diverse range of low-lying and high vegetation on flat terrain. The IEI model can provide input spatial data for high-resolution GIS analysis of hydrological processes. This model will aid decision-makers in stormwater-management, flood-risk assessment, land-use planning, and the design of green infrastructure. By utilizing the information derived from this study, policymakers can make informed decisions to mitigate flooding risks and promote sustainable urban development. [ABSTRACT FROM AUTHOR]

This study employed an ensemble machine learning approach to evaluate the effect of bioclimatic covariates on the prediction accuracy of soil total carbon (TC) in the Pannonian biogeoregion. The analysis involved two main segments: (1) evaluation of base environmental covariates, including surface reflectance, phenology, and derived covariates, compared to the addition of bioclimatic covariates; and (2) assessment of three individual machine learning methods, including random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM), as well as their ensemble for soil TC prediction. Among the evaluated machine learning methods, the ensemble approach resulted in the highest prediction accuracy overall, outperforming the individual models. The ensemble method with bioclimatic covariates achieved an R2 of 0.580 and an RMSE of 10.392, demonstrating its effectiveness in capturing complex relationships among environmental covariates. The results of this study suggest that the ensemble model consistently outperforms individual machine learning methods (RF, XGB, and SVM), and adding bioclimatic covariates improves the predictive performance of all methods. The study highlights the importance of integrating bioclimatic covariates when modeling environmental covariates and demonstrates the benefits of ensemble machine learning for the geospatial prediction of soil TC. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite Systems (GNSS) in precision agriculture (PA) represent a cornerstone for field mapping, machinery guidance, and variable rate technology. However, recent improvements in GNSS components (GPS, GLONASS, Galileo, and BeiDou) and novel remote sensing and computer processing-based solutions in PA have not been comprehensively analyzed in scientific reviews. Therefore, this study aims to explore novelties in GNSS components with an interest in PA based on the analysis of scientific papers indexed in the Web of Science Core Collection (WoSCC). The novel solutions in PA using GNSS were determined and ranked based on the citation topic micro criteria in the WoSCC. The most represented citation topics micro based on remote sensing were "NDVI", "LiDAR", "Harvesting robot", and "Unmanned aerial vehicles" while the computer processing-based novelties included "Geostatistics", "Precise point positioning", "Simultaneous localization and mapping", "Internet of things", and "Deep learning". Precise point positioning, simultaneous localization and mapping, and geostatistics were the topics that most directly relied on GNSS in 93.6%, 60.0%, and 44.7% of the studies indexed in the WoSCC, respectively. Meanwhile, harvesting robot research has grown rapidly in the past few years and includes several state-of-the-art sensors, which can be expected to improve further in the near future. [ABSTRACT FROM AUTHOR]

While SoilGrids is an important source of soil property data for a wide range of environmental studies worldwide, there is currently an extreme lack of studies evaluating its accuracy against independent ground truth soil sampling data. This study aimed to provide a comprehensive insight into the accuracy of SoilGrids layers for three physical soil properties representing soil texture components (clay, silt, and sand soil contents) using ground truth data in the heterogeneous landscape of Croatia. These ground truth data consisted of 686 soil samples collected within the national project at a 0–30 cm soil depth, representing the most recent official national data available. The main specificity of this study was that SoilGrids was created based on zero soil samples in the study area, according to the ISRIC WoSIS Soil Profile Database, which is very sparse for the wider surroundings of the study area. The accuracy assessment metrics indicated an overall low accuracy of the SoilGrids data compared with the ground truth data in Croatia, with the average coefficient of determination (R2) ranging from 0.039 for silt and sand to 0.267 for clay, while the normalized root-mean-square error (NRMSE) ranged from 0.362 to 2.553. Despite the great value of SoilGrids in a vast range of environmental studies, this study proved that the accuracy of its products is highly dependent on the presence of ground truth data in the study area. [ABSTRACT FROM AUTHOR]

Vegetation indices provide information for various precision-agriculture practices, by providing quantitative data about crop growth and health. To provide a concise and up-to-date review of vegetation indices in precision agriculture, this study focused on the major vegetation indices with the criterion of their frequency in scientific papers indexed in the Web of Science Core Collection (WoSCC) since 2000. Based on the scientific papers with the topic of "precision agriculture" combined with "vegetation index", this study found that the United States and China are global leaders in total precision-agriculture research and the application of vegetation indices, while the analysis adjusted for the country area showed much more homogenous global development of vegetation indices in precision agriculture. Among these studies, vegetation indices based on the multispectral sensor are much more frequently adopted in scientific studies than their low-cost alternatives based on the RGB sensor. The normalized difference vegetation index (NDVI) was determined as the dominant vegetation index, with a total of 2200 studies since the year 2000. With the existence of vegetation indices that improved the shortcomings of NDVI, such as enhanced vegetation index (EVI) and soil-adjusted vegetation index (SAVI), this study recognized their potential for enabling superior results to those of NDVI in future studies. [ABSTRACT FROM AUTHOR]

This study presents a micro-scale approach for the cropland suitability assessment of permanent crops based on a low-cost unmanned aerial vehicle (UAV) equipped with a commercially available RGB sensor. The study area was divided into two subsets, with subsets A and B containing tangerine plantations planted during years 2000 and 2008, respectively. The fieldwork was performed on 27 September 2021 by using a Mavic 2 Pro UAV equipped with a commercial RGB sensor. The cropland suitability was performed in a two-step classification process, utilizing: (1) supervised classification with machine learning algorithms for creating a vegetation mask; and (2) unsupervised classification for the suitability assessment according to the Food and Agriculture Organization of the United Nations (FAO) land suitability standard. The overall accuracy and kappa coefficients were used for the accuracy assessment. The most accurate combination of the input data and parameters was the classification using ANN with all nine input rasters, managing to utilize complimentary information regarding the study area spectral and topographic properties. The resulting suitability levels indicated positive suitability in both study subsets, with 63.1% suitable area in subset A and 59.0% in subset B. Despite that, the efficiency of agricultural production can be improved by managing crop and soil properties in the currently non-suitable class (N1), providing recommendations for farmers for further agronomic inspection. Alongside low-cost UAV, the open-source GIS software and globally accepted FAO standard are expected to further improve the availability of its application for permanent crop plantation management. [ABSTRACT FROM AUTHOR]

In recent decades, precision agriculture and geospatial technologies have made it possible to ensure sustainability in an olive-growing sector. The main goal of this study is the extraction of olive tree canopies by comparing two approaches, the first of which is related to geographic object-based analysis (GEOBIA), while the second one is based on the use of vegetation indices (VIs). The research area is a micro-location within the Lun olives garden, on the island of Pag. The unmanned aerial vehicle (UAV) with a multispectral (MS) sensor was used for generating a very high-resolution (VHR) UAVMS model, while another mission was performed to create a VHR digital orthophoto (DOP). When implementing the GEOBIA approach in the extraction of the olive canopy, user-defined parameters and classification algorithms support vector machine (SVM), maximum likelihood classifier (MLC), and random trees classifier (RTC) were evaluated. The RTC algorithm achieved the highest overall accuracy (OA) of 0.7565 and kappa coefficient (KC) of 0.4615. The second approach included five different VIs models (NDVI, NDRE, GNDVI, MCARI2, and RDVI2) which are optimized using the proposed VITO (VI Threshold Optimizer) tool. The NDRE index model was selected as the most accurate one, according to the ROC accuracy measure with a result of 0.888 for the area under curve (AUC). [ABSTRACT FROM AUTHOR]

The most valuable protected natural areas, including national parks, are subjected to the increased visitors count and density, threatening the environmental sustainability and biodiversity conservation. To establish a basis for land management to mitigate these influences, the novel geographic information (GIS)-based environmental susceptibility zoning method was proposed. The study area covered the Plitvice Lakes National Park, as the oldest and largest national park in Croatia, using the historical 20-year visitor data with 19 tourist and hiking routes. Two geospatial analysis methods were evaluated as follows: (1) short-term prediction of visitors count data based on a 10-year historical intervals, and (2) the environmental susceptibility zones delineation method integrated two fundamental factors in the assessment of environmental impacts from route density and historical visitors count on a monthly basis. Four accuracy assessment metrics indicated a moderate accuracy of short-term visitors count prediction, with the coefficient of determination ranging from 0.700 to 0.951. The routes which continue from both entrances indicated the largest visitors load is in the central part of the park, mostly located in the moderately restricted zone. These observations indicated moderate present environmental susceptibility with stable outlook, providing an insight for the nature park management adjustment. [ABSTRACT FROM AUTHOR]

With the emergence of machine learning methods during the past decade, alternatives to conventional geostatistical methods for soil mapping are becoming increasingly more sophisticated. To provide a complete overview of their performance, this study performed cost–benefit analysis of four soil mapping methods based on five criteria: accuracy, processing time, robustness, scalability and applicability. The evaluated methods were ordinary kriging (OK), regression kriging (RK), random forest (RF) and ensemble machine learning (EML) for the prediction of total soil carbon and nitrogen. The results of these mechanisms were objectively standardized using the linear scaling method, and their relative importance was quantified using the analytic hierarchy process (AHP). EML resulted in the highest cost–benefit score of the tested methods, with maximum values of accuracy, robustness and scalability, achieving a 55.6% higher score than the second-ranked RF method. The two geostatistical methods ranked last in the cost–benefit analysis. Despite that, OK could retain its place as the most frequent method for soil mapping in recent studies due to its widespread, user-friendly implementation in GIS software and its univariate character. Further improvement of machine learning methods with regards to computational efficiency could additionally improve their cost–benefit advantage and establish them as the universal standard for soil mapping. [ABSTRACT FROM AUTHOR]

The increasing global demand for food has forced farmers to produce higher crop yields in order to keep up with population growth, while maintaining sustainable production for the environment. As knowledge about natural cropland suitability is mandatory to achieve this, the aim of this paper is to provide a review of methods for suitability prediction according to abiotic environmental criteria. The conventional method for calculating cropland suitability in previous studies was a geographic information system (GIS)-based multicriteria analysis, dominantly in combination with the analytic hierarchy process (AHP). Although this is a flexible and widely accepted method, it has significant fundamental drawbacks, such as a lack of accuracy assessment, high subjectivity, computational inefficiency, and an unsystematic approach to selecting environmental criteria. To improve these drawbacks, methods for determining cropland suitability based on machine learning have been developed in recent studies. These novel methods contribute to an important paradigm shift when determining cropland suitability, being objective, automated, computationally efficient, and viable for widespread global use due to the availability of open data sources on a global scale. Nevertheless, both approaches produce invaluable complimentary benefits to cropland management planning, with novel methods being more appropriate for major crops and conventional methods more appropriate for less frequent crops. [ABSTRACT FROM AUTHOR]

In this study, we propose integrating unmanned aerial systems (UASs) and machine learning classification for suitability prediction of expanding habitats for endangered flora species to prevent further extinction. Remote sensing imaging of the protected steppe-like grassland in Bilje using the DJI P4 Multispectral UAS ensured non-invasive data collection. A total of 129 individual flora units of five endangered flora species, including small pasque flower (Pulsatilla pratensis (L.) Miller ssp. nigricans (Störck) Zämelis), green-winged orchid (Orchis morio (L.)), Hungarian false leopardbane (Doronicum hungaricum Rchb.f.), bloody cranesbill (Geranium sanguineum (L.)) and Hungarian iris (Iris variegate (L.)) were detected and georeferenced. Habitat suitability in the projected area, designated for the expansion of the current area of steppe-like grassland in Bilje, was predicted using the binomial machine learning classification algorithm based on three groups of environmental abiotic criteria: vegetation, soil, and topography. Four machine learning classification methods were evaluated: random forest, XGBoost, neural network, and generalized linear model. The random forest method outperformed the other classification methods for all five flora species and achieved the highest receiver operating characteristic (ROC) values, ranging from 0.809 to 0.999. Soil compaction was the least favorable criterion for the habitat suitability of all five flora species, indicating the need to perform soil tillage operations to potentially enable the expansion of their coverage in the projected area. However, potential habitat suitability was detected for the critically endangered flora species of Hungarian false leopardbane, indicating its habitat-related potential for expanding and preventing further extinction. In addition to the current methods of predicting current coverage and population count of endangered species using UASs, the proposed method could serve as a basis for decision making in nature conservation and land management. [ABSTRACT FROM AUTHOR]

The precision fertilization system is the basis for upgrading conventional intensive agricultural production, while achieving both high and quality yields and minimizing the negative impacts on the environment. This research aims to present the application of both conventional and modern prediction methods in precision fertilization by integrating agronomic components with the spatial component of interpolation and machine learning. While conventional methods were a cornerstone of soil prediction in the past decades, new challenges to process larger and more complex data have reduced their viability in the present. Their disadvantages of lower prediction accuracy, lack of robustness regarding the properties of input soil sample values and requirements for extensive cost- and time-expensive soil sampling were addressed. Specific conventional (ordinary kriging, inverse distance weighted) and modern machine learning methods (random forest, support vector machine, artificial neural networks, decision trees) were evaluated according to their popularity in relevant studies indexed in the Web of Science Core Collection over the past decade. As a shift towards increased prediction accuracy and computational efficiency, an overview of state-of-the-art remote sensing methods for improving precise fertilization was completed, with the accent on open-data and global satellite missions. State-of-the-art remote sensing techniques allowed hybrid interpolation to predict the sampled data supported by remote sensing data such as high-resolution multispectral, thermal and radar satellite or unmanned aerial vehicle (UAV)-based imagery in the analyzed studies. The representative overview of conventional and modern approaches to precision fertilization was performed based on 121 samples with phosphorous pentoxide (P2O5) and potassium oxide (K2O) in a common agricultural parcel in Croatia. It visually and quantitatively confirmed the superior prediction accuracy and retained local heterogeneity of the modern approach. The research concludes that remote sensing data and methods have a significant role in improving fertilization in precision agriculture today and will be increasingly important in the future. [ABSTRACT FROM AUTHOR]

Knowledge of the relationship between soil sampling density and spatial autocorrelation with interpolation accuracy allows more time- and cost-efficient spatial analysis. Previous studies produced contradictory observations regarding this relationship, and this study aims to determine and explore under which conditions the interpolation accuracy of chemical soil properties is affected. The study area covered 823.4 ha of agricultural land with 160 soil samples containing phosphorus pentoxide (P2O5) and potassium oxide (K2O) values. The original set was split into eight subsets using a geographically stratified random split method, interpolated using the ordinary kriging (OK) and inverse distance weighted (IDW) methods. OK and IDW achieved similar interpolation accuracy regardless of the soil chemical property and sampling density, contrary to the majority of previous studies which observed the superiority of kriging as a deterministic interpolation method. The primary dependence of interpolation accuracy to soil sampling density was observed, having R2 in the range of 56.5–83.4% for the interpolation accuracy assessment. While this study enables farmers to perform efficient soil sampling according to the desired level of detail, it could also prove useful to professions dependent on field sampling, such as biology, geology, and mining. [ABSTRACT FROM AUTHOR]

The determination of cropland suitability is a major step for adapting to the increased food demands caused by population growth, climate change and environmental contamination. This study presents a novel cropland suitability assessment approach based on machine learning, which overcomes the limitations of the conventional GIS-based multicriteria analysis by increasing computational efficiency, accuracy and objectivity of the prediction. The suitability assessment method was developed and evaluated for soybean cultivation within two 50 × 50 km subsets located in the continental biogeoregion of Croatia, in the four-year period during 2017–2020. Two biophysical vegetation properties, leaf area index (LAI) and a fraction of absorbed photosynthetically active radiation (FAPAR), were utilized to train and test machine learning models. The data derived from a medium-resolution satellite mission PROBA-V were prime indicators of cropland suitability, having a high correlation to crop health, yield and biomass in previous studies. A variety of climate, soil, topography and vegetation covariates were used to establish a relationship with the training samples, with a total of 119 covariates being utilized per yearly suitability assessment. Random forest (RF) produced a superior prediction accuracy compared to support vector machine (SVM), having the mean overall accuracy of 76.6% to 68.1% for Subset A and 80.6% to 79.5% for Subset B. The 6.1% of the highly suitable FAO suitability class for soybean cultivation was determined on the sparsely utilized Subset A, while the intensively cultivated agricultural land produced only 1.5% of the same suitability class in Subset B. The applicability of the proposed method for other crop types adjusted by their respective vegetation periods, as well as the upgrade to high-resolution Sentinel-2 images, will be a subject of future research. [ABSTRACT FROM AUTHOR]

Interpolation accuracy of the soil carbon-to-nitrogen ratio (C/N) has a direct impact on soil maps for agricultural land management planning, affecting the financial gains of farmers and environmental contamination. This study aimed to evaluate the effect of different ordinary kriging parameters on the interpolation accuracy and spatial variability of soil C/N. These values were necessary to determine the effect of potential soil C/N deficiency on five major crops in the study area during 2017–2019, containing maize, wheat, sunflower, rapeseed and soybean parcels. The Gaussian model with logarithmic transformation produced the higher outer accuracy, representing the prediction accuracy. Average values of final soil C/N rasters resulted as 11.35 at 0–10 cm soil depth and 12.60 at 20–30 cm soil depth, representing values 11.0% higher at a deeper soil layer. The moderate soil N deficiency was observed for all major crops, having soil C/N values mainly higher than 12:1, compared to the optimal value range of 9:1 to 12:1. These observations suggest a need for the adjustment of agricultural land management plans through the regionalization of agricultural production to prevent further soil degradation and ensure optimal crop development conditions. [ABSTRACT FROM AUTHOR]

Soil texture is a vital criterion in most cropland suitability analyses, so an accurate method for the delineation of soil texture suitability zones is necessary. In this study, an automated method was developed and evaluated for the delineation of these zones for soybean cultivation. A total of 255 soil samples were collected in the Continental biogeoregion of Croatia. Three methods for interpolation of clay, silt and sand soil content were evaluated using the split-sample method in five independent random repetitions. An automated algorithm for soil texture classification based on the United States Department of Agriculture (USDA) in 12 classes was performed using Python script. Suitability classes for soybean cultivation per soil texture class were determined according to previous agronomic and soybean land suitability studies. Ordinary kriging produced the highest accuracy of tested interpolation methods for clay, silt and sand. Highly suitable soil texture classes for soybean cultivation, loam and clay loam, were detected in the northern part of the study area, covering 5.73% of the study area. The analysis of classification results per interpolation method indicated a necessity of the evaluation of interpolation methods as their performance depended on the normality and stationarity of input samples. [ABSTRACT FROM AUTHOR]

Soybean is regarded as one of the most produced crops in the world, presenting a source of high-quality protein for human and animal diets. The general objective of the study was to determine the optimal soybean land suitability and conduct its mapping based on the multicriteria analysis. The multicriteria analysis was based on Geographic Information System (GIS) and Analytic Hierarchy Process (AHP) integration, using Sentinel-2 multitemporal images for suitability validation. The study area covered Osijek-Baranja County, a 4155 km2 area located in eastern Croatia. Three criteria standardization methods (fuzzy, stepwise and linear) were evaluated for soybean land suitability calculation. The delineation of soybean land suitability classes was performed by k-means unsupervised classification. An independent accuracy assessment of calculated suitability values was performed by a novel approach with peak Normalized Difference Vegetation Index (NDVI) values, derived from four Sentinel-2 multispectral satellite images. Fuzzy standardization with the combination of soil and climate criteria produced the most accurate suitability values, having the top coefficient of determination of 0.8438. A total of 14.5% of the study area (602 km2) was determined as the most suitable class for soybean cultivation based on k-means classification results, while 64.3% resulted in some degree of suitability. [ABSTRACT FROM AUTHOR]

Red spicy pepper is traditionally considered as the fundamental ingredient for multiple authentic products of Eastern Croatia. The objectives of this study were to: (1) evaluate the optimal interpolation method necessary for modeling of criteria layers; (2) calculate the sustainability and vulnerability of red spicy pepper cultivation using hybrid Geographic Information System (GIS)-based multicriteria analysis with the analytical hierarchy process (AHP) method; (3) determine the suitability classes for red spicy pepper cultivation using K-means unsupervised classification. The inverse distance weighted interpolation method was selected as optimal as it produced higher accuracies than ordinary kriging and natural neighbour. Sustainability and vulnerability represented the positive and negative influences on red spicy pepper production. These values served as the input in the K-means unsupervised classification of four classes. Classes were ranked by the average of mean class sustainability and vulnerability values. Top two ranked classes, highest suitability and moderate-high suitability, produced suitability values of 3.618 and 3.477 out of a possible 4.000, respectively. These classes were considered as the most suitable for red spicy pepper cultivation, covering an area of 2167.5 ha (6.9% of the total study area). A suitability map for red spicy pepper cultivation was created as a basis for the establishment of red spicy pepper plantations. [ABSTRACT FROM AUTHOR]