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.
The accurate detection and treatment of weeds in agricultural fields is a necessary procedure for managing crop yield and avoiding herbicide pollution. With the emergence of unmanned aerial vehicles ...(UAV), the ability to acquire spatial data at the desired spatial and temporal resolution became available, and the resulting input data met high standards for weed management. In this paper, we tested four independent classification algorithms for the creation of weed maps, combining automatic and manual methods, as well as object-based and pixel-based classification approaches, which were used separately on two subsets. Input UAV data were collected using a low-cost RGB camera due to its affordability compared to multispectral cameras. Classification algorithms were based on the random forest machine learning algorithm for weed and bare soil extraction, following an unsupervised classification with the K-means algorithm for further estimation of weeds and bare soil presence in non-weed and non-soil areas. Of the four classification algorithms tested, the automatic object-based classification method achieved the highest classification accuracy, resulting in an overall accuracy of 89.0% for subset A and 87.1% for subset B. Automatic classification methods were robustly developed, using at least 0.25% of the scene size as the training data set in all circumstances anticipated for the random forest classification algorithm to operate. The use of the algorithm resulted in weed maps consisting of zoned classes and covering areas with similar biological properties, making them ready for use as inputs in weed treatments that use agricultural machinery.
Display omitted
•Soil C:N is an indicator of soil quality for sustainable organic farming.•K-means algorithm was implemented for the determination of soil C:N deficiency zones.•Ordinary kriging ...outperformed lognormal kriging and inverse distance weighted.•A total of 45.6% of the study area was determined as unsuitable for organic farming.
Soil carbon-to-nitrogen ratio (C:N) represents an indicator of soil quality and fertility, having a major impact on agricultural land management for organic farming. Determination of soil C:N suitability zones is a necessary procedure in the process, enabling effective land management. A total of 72 soil samples at two soil layers at 0–10 cm and 20–30 cm were used in the study, evenly distributed in the Osijek-Baranja County in eastern Croatia. Ordinary kriging (OK) and Lognormal kriging (LK) using linear, Gaussian and spherical mathematical models, alongside Inverse distance weighted (IDW) were evaluated for the spatial prediction of soil C:N. Inner accuracy representing retention of input sample values in the interpolation results and outer accuracy representing a prediction accuracy at unknown locations were used to determine optimal interpolation parameters. K-means unsupervised classification algorithm was used for the objective determination of soil C:N suitability zones in five classes specified by the Food and Agriculture Organization (FAO). IDW resulted in the highest inner accuracy, while OK with the Gaussian model produced the highest outer accuracy with the average R2 = 0.7908 and NRMSE = 0.0544. Contrary to the previous research, higher mean soil C:N results in a lower soil layer of 20–30 cm with 13.41, compared to 12.03 at 0–10 cm soil layer. The highest soil C:N suitability was determined in only 4.8% of the study area, with the suitability index of 18.44. Meanwhile, the two largest classes were marginally suitable and currently unsuitable class, covering 35.5% and 27.7% of the study area, respectively. These results indicated a necessity for the adjustment of agricultural land management practices to enable sustainable organic farming.
Accurate geospatial prediction of soil parameters provides a basis for large-scale digital soil mapping, making efficient use of the expensive and time-consuming process of field soil sampling. To ...date, few studies have used deep learning for geospatial prediction of soil parameters, but there is evidence that it may provide higher accuracy compared to machine learning methods. To address this research gap, this study proposed a deep neural network (DNN) for geospatial prediction of total soil carbon (TC) in European agricultural land and compared it with the eight most commonly used machine learning methods based on studies indexed in the Web of Science Core Collection. A total of 6209 preprocessed soil samples from the Geochemical mapping of agricultural and grazing land soil (GEMAS) dataset in heterogeneous agricultural areas covering 4,899,602 km2 in Europe were used. Prediction was performed based on 96 environmental covariates from climate and remote sensing sources, with extensive comprehensive hyperparameter tuning for all evaluated methods. DNN outperformed all evaluated machine learning methods (R2 = 0.663, RMSE = 9.595, MAE = 5.565), followed by Quantile Random Forest (QRF) (R2 = 0.635, RMSE = 25.993, MAE = 22.081). The ability of DNN to accurately predict small TC values and thus produce relatively low absolute residuals was a major reason for the higher prediction accuracy compared to machine learning methods. Climate parameters were the main factors in the achieved prediction accuracy, with 23 of the 25 environmental covariates with the highest variable importance being climate or land surface temperature parameters. These results demonstrate the superiority of DNN over machine learning methods for TC prediction, while highlighting the need for more recent soil sampling to assess the impact of climate change on TC content in European agricultural land.
Display omitted
•The deep neural network (DNN) was proposed for the prediction of total soil carbon.•6209 soil samples from agricultural land in Europe were used for prediction.•Hyperparameter tuning was performed for DNN and eight machine learning methods.•DNN had the highest prediction accuracy, followed by quantile random forest (QRF).•Climate and land surface temperature parameters dominated variable importance.
Display omitted
•Thermally pretreated harvest residues and manure were anaerobically co-digested.•Four machine learning methods were tested for biogas and methane yield prediction.•Recursive Feature ...Elimination was the optimal feature selection approach.•R2 for biogas and methane yield prediction was up to 0.820 and 0.823, respectively.•An ensemble machine learning produced stable accuracy regardless of input datasets.
This study aimed to clarify the statistical accuracy assessment approaches used in recent biogas prediction studies using state-of-the-art ensemble machine learning approach according to 10-fold cross-validation in 100 repetitions. Three thermally pretreated harvest residue types (maize stover, sunflower stalk and soybean straw) and manure were anaerobically co-digested, measuring biogas and methane yield alongside eight thermal preprocessing and biomass covariates. These were the inputs to an ensemble machine learning approach for biogas and methane yield prediction, employing three feature selection approaches. The Support Vector Machine prediction with the Recursive Feature Elimination resulted in the highest prediction accuracy, achieving the coefficient of determination of 0.820 and 0.823 for biogas and methane yield prediction, respectively. This study demonstrated an extreme dependency of prediction accuracy to input dataset properties, which could only be mitigated with ensemble machine learning and strongly suggested that the split-sample approach, often used in previous studies, should be avoided.
The increasing wildfire occurrence due to global climate changes urged the improvement of present wildfire growth prediction and evaluation methods. This study aimed to propose novel solutions to ...their two primary limitations, including the lack of robust fuel classification method and the low spatial resolution of wildfire growth accuracy assessment while ensuring wide applicability using open data satellite missions and software. The first objective was to create a robust two-step fuel model classification method consisted of the supervised machine learning classification of generalized land cover classes in the 1st level and their individual unsupervised classification to vegetation subtypes in the 2nd level. The second objective was creating a wildfire prediction accuracy assessment method using MODIS 250 m images, which overcome the limitations of low spatial resolution while preserving sub-daily temporal resolution. The wildfire on the Korčula island in Croatia was analyzed in the study, being specific for its long duration from 18 to 24 July 2015. The wildfire ignition occurred in the isolated area, which prolonged the response time from emergency agencies. Random Forest (RF) with input Landsat 8 spectral bands and indices resulted in the highest classification accuracy in the 1st classification level with an overall agreement of 83.6%. The vegetation subclasses from the 2nd classification level were matched to the 13 standard fuel models for the input in FARSITE software. The predicted wildfire evaluation showed the highest mean accuracy of 0.906 for the first two days, which decreased to 0.722 in the latter stages of the active wildfire caused by overprediction. The proposed two-step fuel model classification presented a cost-efficient solution to the fuel map creation in any part of the world, with a disadvantage of no in-situ ground truth identification and accuracy assessment for 2nd classification level. The evaluation of wildfire growth prediction with 250 m images enabled high spatial and temporal resolution of the assessment, while its limitations of wildfire overprediction and the negative effects of wildfire smoke in MODIS images should be addressed in future research.
Display omitted
•Wildfire growth was predicted and evaluated using Landsat and MODIS images.•The fuel model was classified using a robust two-step classification method.•Wildfire perimeters were evaluated using 250 m daily NDVI time series.•FARSITE prediction mean accuracy was 0.906 in the first two days of active wildfire.•Proposed cost-efficient methods support the decision-making in web services.
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.
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.
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.
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.