Search

Making plant breeding programs less expensive, fast, practical, and accurate, especially for soybeans, promotes the selection of new soybean genotypes and contributes to the emergence of new varieties that are more efficient in absorbing and metabolizing nutrients. Using spectral information from soybean genotypes combined with nutritional information on secondary macronutrients can help genetic improvement programs select populations that are efficient in absorbing and metabolizing these nutrients. In addition, using machine learning algorithms to process this information makes the acquisition of superior genotypes more accurate. Therefore, the objective of the work was to verify the classification performance of soybean genotypes regarding secondary macronutrients by ML algorithms and different inputs. The experiment was conducted in the experimental area of the Federal University of Mato Grosso do Sul, municipality of Chapadão do Sul, Brazil. Soybean was sown in the 2019/20 crop season, with the planting of 103 F2 soybean populations. The experimental design used was randomized blocks, with two replications. At 60 days after crop emergence (DAE), spectral images were collected with a Sensifly eBee RTK fixed-wing remotely piloted aircraft (RPA), with autonomous takeoff control, flight plan, and landing. At the reproductive stage (R1), three leaves were collected per plant to determine the macronutrients calcium (Ca), magnesium (Mg), and sulfur (S) levels. The data obtained from the spectral information and the nutritional values of the genotypes in relation to Ca, Mg, and S were subjected to a Pearson correlation analysis; a PC analysis was carried out with a k-means algorithm to divide the genotypes into clusters. The clusters were taken as output variables, while the spectral data were used as input variables for the classification models in the machine learning analyses. The configurations tested in the models were spectral bands (SBs), vegetation indices (VIs), and a combination of both. The combination of machine learning algorithms with spectral data can provide important biological information about soybean plants. The classification of soybean genotypes according to calcium, magnesium, and sulfur content can maximize time, effort, and labor in field evaluations in genetic improvement programs. Therefore, the use of spectral bands as input data in random forest algorithms makes the process of classifying soybean genotypes in terms of secondary macronutrients efficient and important for researchers in the field. [ABSTRACT FROM AUTHOR]

In addressing the challenges of quantitative precipitation estimation (QPE) using weather radar, the importance of enhancing the rainfall estimates for applications such as flash flood forecasting and hydropower generation management is recognized. This study employed dual-polarization weather radar data to refine the traditional Z–R relationship, which often needs higher accuracy in areas with complex meteorological phenomena. Utilizing tree-based machine learning algorithms, such as random forest and gradient boosting, this research analyzed polarimetric variables to capture the intricate patterns within the Z–R relationship. The results highlight machine learning's potential to improve the precision of precipitation estimation, especially under challenging weather conditions. Integrating meteorological insights with advanced machine learning techniques is a remarkable achievement toward a more precise and adaptable precipitation estimation method. [ABSTRACT FROM AUTHOR]

It is crucial to monitor algal blooms in freshwater reservoirs through an examination of chlorophyll-a (Chla) concentrations, as they indicate the trophic condition of these waterbodies. Traditional monitoring methods, however, are expensive and time-consuming. Addressing this hindrance, we conducted a comprehensive investigation using several machine learning models for Chla modeling. To this end, we used in situ collected water sample data and remote sensing data from the Sentinel-2 satellite, including spectral bands and indices, for large-scale coverage. This approach allowed us to conduct a comprehensive analysis and characterization of the Chla concentrations across 149 freshwater reservoirs in Ceará, a semi-arid region of Brazil. The implemented machine learning models included k-nearest neighbors, random forest, extreme gradient boosting, the least absolute shrinkage, and the group method of data handling (GMDH); in particular, the GMDH approach has not been previously explored in this context. The forward stepwise approach was used to determine the best subset of input parameters. Using a 70/30 split for the training and testing datasets, the best-performing model was the GMDH model, achieving an R2 of 0.91, an MAPE of 102.34%, and an RMSE of 20.4 μg/L, which were values consistent with the ones found in the literature. Nevertheless, the predicted Chla concentration values were most sensitive to the red, green, and near-infrared bands. [ABSTRACT FROM AUTHOR]

At COP26, the Glasgow Leaders Declaration committed to ending deforestation by 2030. Implementing deforestation-free supply chains is of growing importance to importers and exporters but challenging due to the complexity of supply chains for agricultural commodities which are driving tropical deforestation. Monitoring tools are needed that alert companies of forest losses around their source farms. ForestMind has developed compliance monitoring tools for deforestation-free supply chains. The system delivers reports to companies based on automated satellite image analysis of forest loss around farms. We describe an algorithm based on the Python for Earth Observation (PyEO) package to deliver near-real-time forest alerts from Sentinel-2 imagery and machine learning. A Forest Analyst interprets the multi-layer raster analyst report and creates company reports for monitoring supply chains. We conclude that the ForestMind extension of PyEO with its hybrid change detection from a random forest model and NDVI differencing produces actionable farm-scale reports in support of the EU Deforestation Regulation. The user accuracy of the random forest model was 96.5% in Guatemala and 93.5% in Brazil. The system provides operational insights into forest loss around source farms in countries from which commodities are imported. [ABSTRACT FROM AUTHOR]

Mato Grosso state is the biggest maize producer in Brazil, with the predominance of cultivation concentrated in the second harvest. Due to the need to obtain more accurate and efficient data, agricultural intelligence is adapting and embracing new technologies such as the use of satellites for remote sensing and geographic information systems. In this respect, this study aimed to map the second harvest maize cultivation areas at Canarana-MT in the crop year 2019/2020 by using geographic object-based image analysis (GEOBIA) with different spatial, spectral, and temporal resolutions. MSI/Sentinel-2, OLI/Landsat-8, MODIS-Terra and MODIS-Aqua, and PlanetScope imagery were used in this assessment. The maize crops mapping was based on cartographic basis from IBGE (Brazilian Institute of Geography and Statistics) and the Google Earth Engine (GEE), and the following steps of image filtering (gray-level co-occurrence matrix—GLCM), vegetation indices calculation, segmentation by simple non-iterative clustering (SNIC), principal component (PC) analysis, and classification by random forest (RF) algorithm, followed finally by confusion matrix analysis, kappa, overall accuracy (OA), and validation statistics. From these methods, satisfactory results were found; with OA from 86.41% to 88.65% and kappa from 81.26% and 84.61% among the imagery systems considered, the GEOBIA technique combined with the SNIC and GLCM spectral and texture feature discriminations and the RF classifier presented a mapping of the corn crop of the study area that demonstrates an improved and aided the performance of automated multispectral image classification processes. [ABSTRACT FROM AUTHOR]

Brazil is the largest producer and exporter of coffee beans in the world. Given this relevance, it is important to monitor the crop to prevent attacks by pests. This study aimed to detect leaf miner (Leucoptera coffeella) infestation in a newly planted crop based on vegetation indices (VI) derived from aerial images obtained by a multispectral camera embedded in a remotely piloted aircraft (RPA) using random forest (RF). The study was conducted on the Cafua farm in the municipality of Lavras in southern Minas Gerais. The images were collected using a multispectral camera attached to a remotely piloted aircraft (RPA). Collections were carried out on 30 July 2019 (infested crop) and 16 December 2019 (post chemical control). The RF package in R software was used to classify the infested and healthy plants. The t test revealed significant differences in band means between healthy and infested plants, favouring higher means in healthy plants. VI also exhibited significant differences, with EXR being higher in infested plants and GNDVI, GOSAVI, GRRI, MPRI, NDI, NDRE, NDVI and SAVI showing higher averages in healthy plants, indicating distinct spectral responses and light absorption patterns between the two states of the plant. Due to the spectral differences between the classes, it was possible to classify the infested and healthy plants, and the RF algorithm performed very well. [ABSTRACT FROM AUTHOR]

Efficient marketing of winegrapes involves negotiating with potential buyers long before the harvest, when little is known about the expected vintage. Grapevine physiology is affected by weather conditions as well as by soil properties and such information can be applied to build yield prediction models. In this study, Partial Least Squares Regression (PLSR), Cubist (CUB) and Random Forest (RF) algorithms were used to predict yield from imputed weather station data and soil sample analysis reports. Models using only soil variables had the worst general results (R2 = 0.15, RMSE = 4.16 Mg ha−1, MAE = 3.20 Mg ha−1), while the use of only weather variables yielded the best performance (R2 = 0.52, RMSE = 2.99 Mg ha−1, MAE = 2.43 Mg ha−1). Models built with CUB and RF algorithms showed signs of overfitting, yet RF models achieved the best average results (R2 = 0.58, RMSE = 2.85 Mg ha−1, MAE = 2.24 Mg ha−1) using only weather variables as predictors. Weather data imputation affected RF and CUB models more intensely while PLSR remained fairly insensitive. Plant age, yield level group, vineyard plot, May temperatures, soil pH and exchangeable concentrations of Zn, Cu, K and Mn were identified as important predictors. This exploratory work offers insights for future research on grape yield predictive modeling and grouping strategies to obtain more assertive results, thus contributing to a more efficient grapevine production chain in southern Brazil and worldwide. [ABSTRACT FROM AUTHOR]

This study compares the performance of machine learning models for selecting COVID-19 and influenza tests during coexisting outbreaks in Brazil, avoiding the waste of resources in healthcare units. We used COVID-19 and influenza datasets from Brazil to train the Decision Tree (DT), Multilayer Perceptron (MLP), Gradient Boosting Machine (GBM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), K-Nearest Neighbors, Support Vector Machine (SVM), and Logistic Regression algorithms. Moreover, we tested the models using the 10-fold cross-validation method to increase confidence in the results. During the experiments, the GBM, DT, RF, XGBoost, and SVM models showed the best performances, with similar results. The high performance of tree-based models is relevant for the classification of COVID-19 and influenza because they are usually easier to interpret, positively impacting the decision-making of health professionals. [ABSTRACT FROM AUTHOR]

The delineation of management zones is one of the ways to enable the spatially differentiated management of plots using precision agriculture tools. Over the years, the spatial variability of data collected from soil and plant sampling started to be replaced by data collected by proximal and orbital sensors. As a result, the variety and volume of data have increased considerably, making it necessary to use advanced computational tools, such as machine learning, for data analysis and decision-making support. This paper presents a methodology used to establish management zones (MZ) in precision agriculture by analyzing data obtained from soil sampling, proximal sensors and orbital sensors, in experiments carried out in four plots featuring soybean–cotton and soybean–corn crops, in Mato Grosso and Paraná states, Brazil. Four procedures were evaluated, using different input data sets for the MZ delineation: (I) soil attributes, including clay content, apparent electrical conductivity or fertility, along with elevation, yield maps and vegetation indices (VIs) captured during the peak crop biomass period; (II) soil attributes in conjunction with VIs demonstrating strong correlations; (III) solely VIs exhibiting robust correlation with soil attributes and yield; (IV) VIs selected via random forests to identify the importance of the variable for estimating yield. The results showed that the VIs derived from satellite images could effectively replace other types of data. For plots where the natural spatial variability can be easily identified, all procedures favor obtaining MZ maps that allow reductions of 40% to 70% in yield variance, justifying their use. On the other hand, in plots with low natural spatial variability and that do not have reliable yield maps, different data sets used as input do not help in obtaining feasible MZ maps. For areas where anthropogenic activities with spatially differentiated treatment are already present, the exclusive use of VIs for the delineation of MZs must be carried out with reservations. [ABSTRACT FROM AUTHOR]

This work aims to develop a new method to map Land Use and Land Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Land Imager (OLI) data. The novelty of the proposed method consists of selecting the images based on the spectral and temporal characteristics of the LULC classes. First, we defined the six classes to be mapped in the year 2020 as forest, forest plantation, water bodies, urban areas, agriculture, and pasture. Second, we visually analyzed their variability spectral characteristics over the year. Then, we pre-processed these images to highlight each LULC class. For the classification, the Random Forest algorithm available on the Google Earth Engine (GEE) platform was utilized individually for each LULC class. Afterward, we integrated the classified maps to create the final LULC map. The results revealed that forest areas are primarily concentrated in the eastern region of São Paulo, predominantly on steeper slopes, accounting for 19% of the study area. On the other hand, pasture and agriculture dominated 73% of all São Paulo's landscape, reaching 39% and 34%, respectively. The overall accuracy of the classification achieved 89.10%, while producer and user accuracies were greater than 84.20% and 76.62%, respectively. To validate the results, we compared our findings with the MapBiomas Project classification, obtaining an overall accuracy of 85.47%. Therefore, our method demonstrates its potential to minimize classification errors and offers the advantage of facilitating post-classification editing for individual mapped classes. [ABSTRACT FROM AUTHOR]

The most common methods to detect non-technical losses involve Deep Learning-based classifiers and samples of consumption remotely collected several times a day through Smart Meters (SMs) and Advanced Metering Infrastructure (AMI). This approach requires a huge amount of data, and training is computationally expensive. However, most energy meters in emerging countries such as Brazil are technologically limited. These devices can measure only the accumulated energy consumption monthly. This work focuses on detecting energy theft in scenarios without AMI and SM. We propose a strategy called HyMOTree intended for the hyperparameter tuning of tree-based algorithms using different multiobjective optimization strategies. Our main contributions are associating different multiobjective optimization strategies to improve the classifier performance and analyzing the model's performance given different probability cutoff operations. HyMOTree combines NSGA-II and GDE-3 with Decision Tree, Random Forest, and XGboost. A dataset provided by a Brazilian power distribution company CPFL ENERGIA™ was used, and the SMOTE technique was applied to balance the data. The results show that HyMOTree performed better than the random search method, and then, the combination between Random Forest and NSGA-II achieved 0.95 and 0.93 for Precision and F1-Score, respectively. Field studies showed that inspections guided by HyMOTree achieved an accuracy of 76%. [ABSTRACT FROM AUTHOR]

The differentiation between the main crop and weeds is an important step for selective spraying systems to avoid agrochemical waste and reduce economic and environmental impacts. In this sense, this study aims to classify and map the area occupied by weeds, determine the percentage of area occupied, and indicate treatment control strategies to be adopted in the field. This study was conducted by using a yellow Bourbon cultivar (IAC J10) with 1 year of implementation on a commercial coffee plantation located at Minas Gerais, Brazil. The aerial images were obtained by a remotely piloted aircraft (RPA) with an embedded multispectral sensor. Image processing was performed using PIX4D, and data analysis was performed using R and QGIS. The random forest (RF) and support vector machine (SVM) algorithms were used for the classification of the regions of interest: coffee, weed, brachiaria, and exposed soil. The differentiation between the study classes was possible due to the spectral differences between the targets, with better classification performance using the RF algorithm. The savings gained by only treating areas with the presence of weeds compared with treating the total study area are approximately 92.68%. [ABSTRACT FROM AUTHOR]

Regenerative agricultural practices are a suitable path to feed the global population. Integrated Crop–livestock systems (ICLSs) are key approaches once the area provides animal and crop production resources. In Brazil, the expectation is to increase the area of ICLS fields by 5 million hectares in the next five years. However, few methods have been tested regarding spatial and temporal scales to map and monitor ICLS fields, and none of these methods use SAR data. Therefore, in this work, we explored the potential of three machine and deep learning algorithms (random forest, long short-term memory, and transformer) to perform early-season (with three-time windows) mapping of ICLS fields. To explore the scalability of the proposed methods, we tested them in two regions with different latitudes, cloud cover rates, field sizes, landscapes, and crop types. Finally, the potential of SAR (Sentinel-1) and optical (Sentinel-2) data was tested. As a result, we found that all proposed algorithms and sensors could correctly map both study sites. For Study Site 1(SS1), we obtained an overall accuracy of 98% using the random forest classifier. For Study Site 2, we obtained an overall accuracy of 99% using the long short-term memory net and the random forest. Further, the early-season experiments were successful for both study sites (with an accuracy higher than 90% for all time windows), and no significant difference in accuracy was found among them. Thus, this study found that it is possible to map ICLSs in the early-season and in different latitudes by using diverse algorithms and sensors. [ABSTRACT FROM AUTHOR]

The coffee leaf miner (Leucoptera coffeella) is a key coffee pest in Brazil that can cause severe defoliation and a negative impact on the productivity. Thus, it is essential to identify initial pest infestation for the sake of appropriate time control to avoid further economic damage to the coffee crops. A fast non-destructive method is an important tool that can be used to monitor the occurrence of the coffee leaf miner. The present work aims to identify the occurrence of coffee leaf miner infestation through a new vegetation index, using multispectral images from the Sentinel-2 satellite and the Google Earth Engine platform. Coffee leaf miner infestation was measured in the field in four cities in the state of Minas Gerais. The largest infestations occurred in September, October, and November but particularly in October 2021, in which the rate of infestation reached 85%, followed by September 2020 with a maximum infestation of 76%. The calculation steps of the vegetation indices and mappings were carried out in the Google Earth Engine cloud processing platform through the development of a script in JavaScript programming language. Combinations of two sensitive bands were selected to detect coffee leaf miner infestation, and from these, the "Coffee-Leaf-Miner Index" was developed, which was compared with other existing vegetation indices in terms of their performance for coffee leaf miner detection. The combination of the NIR–BLUE and NIR–RED bands was more sensitive for the detection of coffee leaf miner infestation; therefore, the NIR, BLUE, and RED bands were selected to develop the new index. The "Coffee-Leaf-Miner Index" presented the best performance among those evaluated, with a coefficient of determination of about 0.87, a root mean square error of 4.92% coffee leaf miner infestation, accuracy of 89.47%, and kappa coefficient of 95.39. The R2 range of other spectral indices which exist in the literature and which were used in this study was from 0.017 to 0.867, and the root mean square error ranged from 4.996 to 13.582% coffee leaf miner infestation. The machine learning method was then adopted using the supervised Random Forest and Support Vector Machine algorithms to recognize patterns of coffee leaf miner infestation in the field, only the Coffee-Leaf-Miner Index was used for the identification test of the coffee leaf miner infestation. The Support Vector Machine with linear Kernel type was applied to establish a discrimination model. The number of trees for the Random Forest classifier was 100. The Support Vector Machine presented a lower performance than the Random Forest algorithm, but the performance of both were above 80% for user and producer precision. Three bands (Blue, Red, NIR) were selected for the creation of the new index, which showed capacity for remote detection of coffee leaf miner infestation on a regional scale. Thus, "Coffee-Leaf-Miner Index" can identify coffee leaf miner infestation thanks to all the complexity involved in detecting pests via orbital remote sensing. [ABSTRACT FROM AUTHOR]

Irrigation is important for agricultural production and is often decisive for this, especially in arid and semi-arid areas, where precipitation is insufficient. In Brazil, irrigated agriculture is responsible for 46% of withdrawals from water bodies and 67% of the consumption of the total volume of water collected, representing the highest consumptive use in the country. Remote sensing technologies have great potential for developing methods for monitoring irrigated areas. However, mapping irrigated areas is still a challenge, due to the complexity and diversity of irrigation methods and crops, especially in a country with continental dimensions like Brazil. Remote sensing techniques for mapping irrigated areas in Brazil have been applied mainly in areas with center pivot irrigation in the Cerrado, and with paddy rice in the south of Brazil. But few or no applications, involving mapping of crops irrigated by other irrigation methods, mainly in the semi-arid, have been carried out. The objective of this work was to investigate a method for classifying irrigated agriculture in a semiarid region of Brazil, based on the use of Sentinel 2 imagery and random forest algorithm. We proposed a novel and robust methodology showing with preliminary results that it's possible to identify irrigated agriculture in this region with a class-f1-score of 74% for complementary irrigation and 95% for center-pivots. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Management Analysis / Revista Gestão em Análise is the property of Revista Gestao em Analise and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Acta Paulista de Enfermagem is the property of Universidade Federal de Sao Paulo, Escola Paulista de Enfermagem and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Yellow fever virus (YFV) is the agent of the most severe mosquito-borne disease in the tropics. Recently, Brazil suffered major YFV outbreaks with a high fatality rate affecting areas where the virus has not been reported for decades, consisting of urban areas where a large number of unvaccinated people live. We developed a machine learning framework combining three different algorithms (XGBoost, random forest and regularized logistic regression) to analyze YFV genomic sequences. This method was applied to 56 YFV sequences from human infections and 27 from non-human primate (NHPs) infections to investigate the presence of genetic signatures possibly related to disease severity (in human related sequences) and differences in PCR cycle threshold (Ct) values (in NHP related sequences). Our analyses reveal four non-synonymous single nucleotide variations (SNVs) on sequences from human infections, in proteins NS3 (E614D), NS4a (I69V), NS5 (R727G, V643A) and six non-synonymous SNVs on NHP sequences, in proteins E (L385F), NS1 (A171V), NS3 (I184V) and NS5 (N11S, I374V, E641D). We performed comparative protein structural analysis on these SNVs, describing possible impacts on protein function. Despite the fact that the dataset is limited in size and that this study does not consider virus-host interactions, our work highlights the use of machine learning as a versatile and fast initial approach to genomic data exploration. [ABSTRACT FROM AUTHOR]

Tropical and subtropical regions shelter high levels of biodiversity. A combination of biological, environmental and anthropogenic factors influences tree community diversity and composition. Here, we use data from the IFFSC project to test the effect of conspecific and heterospecific density dependence, canopy cover and distance to edge on saplings populations of 229 woody species in 159 plots distributed across three forest types in Southern Brazil. All plots were measured twice with a standardized time interval of 5 years. We fitted one ordinary least square regression model to each species to test the strength of each predictor on the species' population growth rate, and one global mixed effect model including forest type, ecological group and the interaction between distance to edge and conspecific density to test their impact in the overall trend of the species. Our analysis provided circumstantial evidence that conspecific density dependence is shaping diversity of forest fragments. This mechanism was present for 75.5% of the species, while heterospecific density affected 10% of the species. Canopy cover affected the population dynamics of 9.2% of the species and distance to edge affected 7.4% of the species. Forest type had a significant effect in the global model, suggesting that population dynamics differ between different forest formations. Ecological group was not significant in the global model suggesting that the mechanism affects species similarly despite their ecological group. The interaction between distance to edge and conspecific density was significant in the global model, suggesting that this mechanism differs between interior and edge of fragments. This work represents one of the few large‐scale analyses of conspecific density dependence in fragmented secondary forests. Our results show that, once the forest is stablished, conspecific density dependence is crucial in sapling population dynamics, despite high levels of fragmentation. [ABSTRACT FROM AUTHOR]

Despite the increasing adoption of proximal sensors worldwide, rare works have coupled proximal with remotely sensed data to spatially predict soil properties. This study evaluated the contribution of proximal and remotely sensed data to predict soil texture and available contents of micronutrients using portable X-ray fluorescence (pXRF) spectrometry, magnetic susceptibility (MS), and terrain attributes (TA) via random forest algorithm. Samples were collected in Brazil from soils with high, moderate, and low weathering degrees (Oxisols, Ultisols, Inceptisols, respectively), and analyzed by pXRF and MS and for texture and available micronutrients. Seventeen TA were generated from a digital elevation model of 12.5 m spatial resolution. Predictions were made via: (i) TA; (ii) TA + pXRF; (iii) TA + MS; (iv) TA + MS + pXRF; (v) MS + pXRF; and (vi) pXRF; and validated via root mean square error (RMSE) and coefficient of determination (R2). The best predictions were achieved by: pXRF dataset alone for available Cu (R² = 0.80) and clay (R2 = 0.67) content; MS + pXRF dataset for available Fe (R2 = 0.68) and sand (R2 = 0.69) content; TA + pXRF + MS dataset for available Mn (R2 = 0.87) content. PXRF data were key to the best predictions. Soil property maps created from these predictions supported the adoption of sustainable soil management practices. [ABSTRACT FROM AUTHOR]

Identifying nematode damage in large soybean areas is not always achievable in a practical way. Multispectral reflectance sensors have not been thoroughly evaluated to detect nematode damage in soybeans (Glycine max L.). The main research aims of this study were to: (i) determine the bivariate relationship between individual spectral bands and vegetation indices (VIs) relative to soybean conditions (symptomatic versus asymptomatic), and (ii) to select the best model for identifying plant conditions using three algorithms (logistic regression—LR, random forest—RF, conditional inference tree—CIT) and three options for data input using bands, vegetation indices (VIs), and bands plus VIs. The trial was conducted in Brazil on three on-farm soybean fields presenting different species of nematode infestation. Multispectral imagery was obtained using a drone-mounted MicaSense RedEdge® sensor. At each sampling, georeferenced point nematode infestation and spectral measurements of soybean plants were retrieved for the classification of symptomatic and asymptomatic areas, according to the threshold level adopted. Bivariate analysis of variance (ANOVA), LR, RF, and CIT were used to select the multispectral bands/VIs that discriminated among symptomatic and asymptomatic plants, assessing the best model via their respective parameters for accuracy, sensitivity, and specificity. The greatest classification accuracy (>0.70) was achieved when using the CIT algorithm with the spectral bands only, with green (560 ± 20 nm) and near-infrared (840 ± 40 nm) included as the main spectral input variables in the model. These results demonstrate the potential of combining remotely sensed data and machine learning to distinguish nematode-symptomatic and asymptomatic soybean plants. [ABSTRACT FROM AUTHOR]

Dengue is a serious public health concern in Brazil and globally. In the absence of a universal vaccine or specific treatments, prevention relies on vector control and disease surveillance. Accurate and early forecasts can help reduce the spread of the disease. In this study, we developed a model for predicting monthly dengue cases in Brazilian cities 1 month ahead, using data from 2007–2019. We compared different machine learning algorithms and feature selection methods using epidemiologic and meteorological variables. We found that different models worked best in different cities, and a random forests model trained on monthly dengue cases performed best overall. It produced lower errors than a seasonal naive baseline model, gradient boosting regression, a feed-forward neural network, or support vector regression. For each city, we computed the mean absolute error between predictions and true monthly numbers of dengue cases on the test data set. The median error across all cities was 12.2 cases. This error was reduced to 11.9 when selecting the optimal combination of algorithm and input features for each city individually. Machine learning and especially decision tree ensemble models may contribute to dengue surveillance in Brazil, as they produce low out-of-sample prediction errors for a geographically diverse set of cities. [ABSTRACT FROM AUTHOR]

Tree growth models are an important and essential part of modeling forest dynamics and valuable tools for management planning and biodiversity conservation strategies. We applied three different machine learning models, namely Artificial Neural Networks (ANN), Support Vector Machine (SVM) and Random Forest (RF) models to predict tree growth at the plot-level in the Atlantic Forest of Brazil. Forest attributes, land use history, landscape, soil and climatic characteristics were used in the modeling. Recursive Feature Elimination (RF) was used to select the best subset of predictor variables. We found that edaphic, forest attributes and climatic variables are important in shaping growth in the Brazilian Atlantic Forest. Soil acidity was the most important characteristic. The machine learning methods were efficient. The Random Forest method showed superiority over the others for modeling growth in the Atlantic Forest. The Nemenyi test pointed out that the difference between the RF model and the other techniques was greater than the calculated Critical Difference (CD). Machine learning can be an important tool for modeling growth in forest fragments in the Brazilian Atlantic Forest. They can help in understanding the biome and in developing management strategies aimed at recovering biodiversity and reducing the deleterious effects of fragmentation. • Machine learning techniques were utilized to model forests in the Atlantic Forest region. • The modeling process incorporated various factors, including forest attributes, land use history, landscape features, soil characteristics, and climate data. • The research findings highlighted the significance of these factors in shaping growth patterns within the Brazilian Atlantic Forest. • Random Forest method outperformed other approaches to modeling forest growth in the Atlantic Forest. [ABSTRACT FROM AUTHOR]

Spatial patterns of stable isotopes in animal tissues or "isoscapes" can be used to investigate animal origins in a range of ecological and forensic investigations. Here, we developed a feather hydrogen isotope (δ2Hf) isoscape for Brazil based on 192 samples of feathers from the family Thraupidae from scientific collections. Raw values of δ2Hf ranged from -107.3 to +5.0‰, with higher values at the Caatinga biome (northeast Brazil) and lower values at the Amazon and Pantanal. A Random Forest (RF) method was used to model the spatial surface, using a range of environmental data as auxiliary variables. The RF model indicated a negative relationship between δ2Hf and Mean Annual Precipitation, Precipitation in the Warmest Quarter, and Annual Temperature Range and positive relationships for amount-weighted February-April precipitation δ2H (δ2Hp(Feb-April)) and Mean Annual Solar Radiation. Modelled δ2Hf values ranged from -85.7 to -13.6‰. Ours is the first δ2Hf isoscape for Brazil that can greatly assist our understanding of both ecological and biogeochemical processes controlling spatial variation in δ2H for this region. This isoscape can be used with caution, due to its poor predictive power (as found in other tropical regions) and can benefit from new sample input, new GNIP data, ecological and physiological studies, and keratin standard material better encompassing the range in feather samples from Brazil. So, we encourage new attempts to build more precise feather H isoscapes, as well as isoscapes based on other elements. [ABSTRACT FROM AUTHOR]

Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative datasets is required. As a result, techniques for selecting point locations to represent negative examples must be employed. Several approaches have been proposed in the past; however, one can never be certain that the points chosen are true negatives or, at the very least, optimal for training. As a consequence, methodologies that account for the uncertainty of the generation of negative datasets in MPM are needed. In this paper, we compare two criteria for selecting negative examples and quantify the uncertainty associated with this process by generating 400 potential maps for each of the three ML methods utilized (200 maps for each criterion), which include random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNC). The results showed that applying a geological constraint to the creation of negative datasets reduced prediction uncertainty and improved overall model performance but produced larger areas of very high probability (i.e., >0.9) when compared to using only the spatial distribution of known deposits and occurrences as a constraint. SHAP values were used to find approximations for the importance of features in nonlinear methods, and kernel density estimations were used to examine how they varied depending on the negative dataset used to train the ML models. Prospectivity models for magmatic-hydrothermal gold deposits were generated using data from the shuttle radar terrain mission, gamma-ray, magnetic lineaments, and proximity to dykes. The Juruena Mineral Province, situated in Northern Mato Grosso, Brazil, represented the case study for this work. [ABSTRACT FROM AUTHOR]

Every year, deforestation results in the loss of wide stretches of forest which is worsening the state of air quality, biodiversity, indigenous cultures, climate, meteorological conditions, etc. According to the Monitoring of the Andean Amazon Project (MAAP), roughly 20 million hectares of land were lost due to deforestation in 2020. To address the issue of deforestation, this study proposes a derivation of the deforestation risk model to target the spread of deforestation, which is the first step towards its prevention. The region of interest - North West of Mato Grosso, Brazil - was selected based on two characteristics: it is a deforestation hotspot according to MAAP and it comprises 4 indigenous lands. The sequence for developing the risk model comprises reference information collection, information cleaning, classification, postprocessing, and change detection. In a crowdsourcing mapathon, reference data were gathered, and they were refined in an iterative process using existing land cover maps and photo interpretation. Google Earth Engine and the Random Forest algorithm were used to classify Sentinel-2 imagery for 2019 and 2020. The results obtained are land cover maps from 2019 and 2020 and land cover change, and the risk model. The results are not demonstrating intensive deforestation in the region of interest, however, the deforestation appears to be systematic in two subregions, indicating that it has the potential to spread. An additional concern in the case of these subregions is their proximity to the indigenous land. [ABSTRACT FROM AUTHOR]

Brazil has established itself as one of the world leaders in food production. Different types of remote sensing mapping techniques have been undertaken to support rural planning in the country. However, due to the complex dynamics of Brazilian agriculture, especially in the Cerrado biome (tropical savanna), there is a need for more feasible crop discrimination and monitoring initiatives, which require a consistent time series of remote sensing data at medium meter and potentially up to 3 day Landsat 8 and Sentinel-2 satellite time series, minimizing the cloud cover limitations for rainfed agricultural monitoring. This paper aims to explore the potential of the Harmonized Landsat 8 Sentinel-2 (HLS) data cube to map agricultural landscapes in the Brazilian Cerrado. The HLS multispectral bands from 27 scenes with less than 10% cloud cover, from October 2020 to September 2021, encompassing one entire crop growing season, were processed by the Random Forest algorithm to produce a map with four land use/cover classes (annual crops, sugarcane, renovated sugarcane fields, cultivated pastures, and native Cerrado). We performed accuracy assessment through 10-fold cross-validation and confusion matrix analyses. The results showed a high level of overall accuracy and Kappa coefficient, both with 99%, as well as high user's and producer's accuracies of at least 99%. The HLS dataset has been continuously improved, showing very promising results for rainfed agricultural mapping and monitoring. [ABSTRACT FROM AUTHOR]

PlanetScope (PL) high-resolution composite base maps have recently become available within Google Earth Engine (GEE) for the tropical regions thanks to the partnership between Google and the Norway's International Climate and Forest Initiative (NICFI). Object-based (OB) image classification in the GEE environment has increased rapidly due to the broadly recognized advantages of applying these approaches to medium- and high-resolution images. This work aimed to assess the advantages for land cover classification of (a) adopting an OB approach with PL data; and (b) integrating the PL datasets with Sentinel 2 and Sentinel 1 data both in Pixel-based (PB) or OB approaches. For this purpose, in this research, we compared ten LULC classification approaches (PB and OB, all based on the Random Forest (RF) algorithm), where the three satellite datasets were used according to different levels of integration and combination. The study area, which is 69,272 km2 wide and located in central Brazil, was selected within the tropical region, considering a preliminary availability of sample points and its complex landscape mosaic composed of heterogeneous agri-natural spaces, including scattered settlements. Using only the PL dataset with a typical RF PB approach produced the worse overall accuracy (OA) results (67%), whereas adopting an OB approach for the same dataset yielded very good OA (82%). The integration of PL data with the S2 and S1 datasets improved both PB and OB overall accuracy outputs (82 vs. 67% and 91 vs. 82%, respectively). Moreover, this research demonstrated the OB approaches' applicability in GEE, even in vast study areas and using high-resolution imagery. Although additional applications are necessary, the proposed methodology appears to be very promising for properly exploiting the potential of PL data in GEE. [ABSTRACT FROM AUTHOR]

The importance of daily data on reference evapotranspiration (ET0) has increased in recent years due to its relevance in planning and decision making regarding irrigated agriculture, water production, and forest restoration. Facing the scarcity of this information measured in loco, the study of interpolation methods capable of representing ET0 becomes important. Therefore, this study aimed to evaluate the adequacy of the Random Forest (RF) method in the spatialization of ET0 in the watersheds of the Mid-South region of the Espírito Santo State, located within the Atlantic Forest biome, Brazil. From this study, it was found that the RF method is the most suitable one for ET0 spatialization when compared to the Angular distance weighting (ADW) and the inverse distance weighting (IDW) techniques. Also, the spatializations carried out by this method were transformed into databases in a grid format and made available online. Furthermore, the RF database was also compared to other ET0 grid databases, and it was concluded that the RF database also carried out a better performance than the other ones. [ABSTRACT FROM AUTHOR]

Brazil presents large yield gaps in garlic crops partly due to nutrient mismanagement at local scale. Machine learning (ML) provides powerful tools to handle numerous combinations of yield-impacting factors that help reducing the number of assumptions about nutrient management. The aim of the current study is to customize fertilizer recommendations to reach high garlic marketable yield at local scale in a pilot study. Thus, collected 15 nitrogen (N), 24 phosphorus (P), and 27 potassium (K) field experiments conducted during the 2015 to 2017 period in Santa Catarina state, Brazil. In addition, 61 growers' observational data were collected in the same region in 2018 and 2019. The data set was split into 979 experimental and observational data for model calibration and into 45 experimental data (2016) to test ML models and compare the results to state recommendations. Random Forest (RF) was the most accurate ML to predict marketable yield after cropping system (cultivar, preceding crops), climatic indices, soil test and fertilization were included features as predictor (R2 = 0.886). Random Forest remained the most accurate ML model (R2 = 0.882) after excluding cultivar and climatic features from the prediction-making process. The model suggested the application of 200 kg N ha-1 to reach maximum marketable yield in a test site in comparison to the 300 kg N ha-1 set as state recommendation. P and K fertilization also seemed to be excessive, and it highlights the great potential to reduce production costs and environmental footprint without agronomic loss. Garlic root colonization by arbuscular mycorrhizal fungi likely contributed to P and K uptake. Well-documented data sets and machine learning models could support technology transfer, reduce costs with fertilizers and yield gaps, and sustain the Brazilian garlic production. [ABSTRACT FROM AUTHOR]

Solar irradiance forecasting has been an essential topic in renewable energy generation. Forecasting is an important task because it can improve the planning and operation of photovoltaic systems, resulting in economic advantages. Traditionally, single models are employed in this task. However, issues regarding the selection of an inappropriate model, misspecification, or the presence of random fluctuations in the solar irradiance series can result in this approach underperforming. This paper proposes a heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance. For each unseen test pattern, HetDS chooses the most suitable forecasting model based on a pool of seven well-known literature methods: ARIMA, support vector regression (SVR), multilayer perceptron neural network (MLP), extreme learning machine (ELM), deep belief network (DBN), random forest (RF), and gradient boosting (GB). The experimental evaluation was performed with four data sets of hourly solar irradiance measurements in Brazil. The proposed model attained an overall accuracy that is superior to the single models in terms of five well-known error metrics. [ABSTRACT FROM AUTHOR]

Broiler meat is the second world's most consumed meat, and the increase in consumption by 2027 is forecasted to be near 35 kg/capita/year. Brazil ranks third in broiler production globally and is the world's largest exporter of chicken meat. To reach proper rearing conditions, broiler farms need to meet good practices of husbandry and welfare. The present study aimed to develop a performance classification model using data mining to evaluate broiler farmers based on detailed flock housing and performance information. The input dataset from 49 broiler farms from a cooperative in Northeastern Brazil was organized with details on the housing characteristics, rearing environment, management, and performance data from flocks. We also added the cooperative technical classification retrieved from the housing conditions and the production index. The input classification had weights attributed to each housing feature. The output variable (target) was defined as the performance classification (PC) index. The dataset was processed using Rapidminer® software using 80% of training and 20% for implementing the random forest algorithm. The prominent variables in classifying the performance were the feed conversion, the daily weight gain, the productivity index, and the cooperative classification criteria. The developed model pointed out a way to auto-classify farms and allow the cooperative to evaluate the farmers' production based on the broiler production and management practices. It was possible to create 'If-Then' rules that enable appropriate decisionmaking by broiler farmers to comply with good practices' norms. [ABSTRACT FROM AUTHOR]

This study aims to develop an assumption-free data-driven model to accurately forecast COVID-19 spread. Towards this end, we firstly employed Bayesian optimization to tune the Gaussian process regression (GPR) hyperparameters to develop an efficient GPR-based model for forecasting the recovered and confirmed COVID-19 cases in two highly impacted countries, India and Brazil. However, machine learning models do not consider the time dependency in the COVID-19 data series. Here, dynamic information has been taken into account to alleviate this limitation by introducing lagged measurements in constructing the investigated machine learning models. Additionally, we assessed the contribution of the incorporated features to the COVID-19 prediction using the Random Forest algorithm. Results reveal that significant improvement can be obtained using the proposed dynamic machine learning models. In addition, the results highlighted the superior performance of the dynamic GPR compared to the other models (i.e., Support vector regression, Boosted trees, Bagged trees, Decision tree, Random Forest, and XGBoost) by achieving an averaged mean absolute percentage error of around 0.1%. Finally, we provided the confidence level of the predicted results based on the dynamic GPR model and showed that the predictions are within the 95% confidence interval. This study presents a promising shallow and simple approach for predicting COVID-19 spread. [ABSTRACT FROM AUTHOR]

Native vegetation across the Brazilian Cerrado is highly heterogeneous and biodiverse and provides important ecosystem services, including carbon and water balance regulation, however, land-use changes have been extensive. Conservation and restoration of native vegetation is essential and could be facilitated by detailed landcover maps. Here, across a large case study region in Goiás State, Brazil (1.1 Mha), we produced physiognomy level maps of native vegetation (n = 8) and other landcover types (n = 5). Seven different classification schemes using different combinations of input satellite imagery were used, with a Random Forest classifier and 2-stage approach implemented within Google Earth Engine. Overall classification accuracies ranged from 88.6–92.6% for native and non-native vegetation at the formation level (stage-1), and 70.7–77.9% for native vegetation at the physiognomy level (stage-2), across the seven different classifications schemes. The differences in classification accuracy resulting from varying the input imagery combination and quality control procedures used were small. However, a combination of seasonal Sentinel-1 (C-band synthetic aperture radar) and Sentinel-2 (surface reflectance) imagery resulted in the most accurate classification at a spatial resolution of 20 m. Classification accuracies when using Landsat-8 imagery were marginally lower, but still reasonable. Quality control procedures that account for vegetation burning when selecting vegetation reference data may also improve classification accuracy for some native vegetation types. Detailed landcover maps, produced using freely available satellite imagery and upscalable techniques, will be important tools for understanding vegetation functioning at the landscape scale and for implementing restoration projects. [ABSTRACT FROM AUTHOR]

The dengue virus affects millions of people every year worldwide, causing large epidemic outbreaks that disrupt people's lives and severely strain healthcare systems. In the absence of a reliable vaccine against dengue or an effective treatment to manage the illness in humans, most efforts to combat dengue infections have focused on preventing its vectors, mainly the Aedes aegypti mosquito, from flourishing across the world. These mosquito-control strategies need reliable disease activity surveillance systems to be deployed. Despite significant efforts to estimate dengue incidence using a variety of data sources and methods, little work has been done to understand the relative contribution of the different data sources to improved prediction. Additionally, scholarship on the topic had initially focused on prediction systems at the national- and state-levels, and much remains to be done at the finer spatial resolutions at which health policy interventions often occur. We develop a methodological framework to assess and compare dengue incidence estimates at the city level, and evaluate the performance of a collection of models on 20 different cities in Brazil. The data sources we use towards this end are weekly incidence counts from prior years (seasonal autoregressive terms), weekly-aggregated weather variables, and real-time internet search data. We find that both random forest-based models and LASSO regression-based models effectively leverage these multiple data sources to produce accurate predictions, and that while the performance between them is comparable on average, the former method produces fewer extreme outliers, and can thus be considered more robust. For real-time predictions that assume long delays (6–8 weeks) in the availability of epidemiological data, we find that real-time internet search data are the strongest predictors of dengue incidence, whereas for predictions that assume short delays (1–3 weeks), in which the error rate is halved (as measured by relative RMSE), short-term and seasonal autocorrelation are the dominant predictors. Despite the difficulties inherent to city-level prediction, our framework achieves meaningful and actionable estimates across cities with different demographic, geographic and epidemic characteristics. Author summary: As the incidence of infectious diseases like dengue continues to increase throughout the world, tracking their spread in real time poses a significant challenge to local and national health authorities. Accurate incidence data are often difficult to obtain as outbreaks emerge and unfold, both due the partial reach of serological surveillance (especially in rural areas), and due to delays in reporting, which result in post-hoc adjustments to what should have been real-time data. Thus, a range of 'nowcasting' tools have been developed to estimate disease trends, using different mathematical and statistical methodologies to fill the temporal data gap. Over the past several years, researchers have investigated how to best incorporate internet search data into predictive models, since these can be obtained in real-time. Still, most such models have been regression-based, and have tended to underperform in cases when epidemiological data are only available after long reporting delays. Moreover, in tropical countries, attention has increasingly turned from testing and applying models at the national level to models at higher spatial resolutions, such as states and cities. Here, we develop machine learning models based on both LASSO regression and on random forest ensembles, and proceed to apply and compare them across 20 cities in Brazil. We find that our methodology produces meaningful and actionable disease estimates at the city level with both underlying model classes, and that the two perform comparably across most metrics, although the ensemble method produces fewer outliers. We also compare model performance and the relative contribution of different data sources across diverse geographic, demographic and epidemic conditions. [ABSTRACT FROM AUTHOR]

Introduction: Recent research has suggested an increase in the global prevalence of psychiatric symptoms during the COVID-19 pandemic. This study aimed to assess whether lifestyle behaviors can predict the presence of depression and anxiety in the Brazilian general population, using a model developed in Spain. Methods: A web survey was conducted during April-May 2020, which included the Short Multidimensional Inventory Lifestyle Evaluation (SMILE) scale, assessing lifestyle behaviors during the COVID-19 pandemic. Depression and anxiety were examined using the PHQ-2 and the GAD-7, respectively. Elastic net, random forest, and gradient tree boosting were used to develop predictive models. Each technique used a subset of the Spanish sample to train the models, which were then tested internally (vs. the remainder of the Spanish sample) and externally (vs. the full Brazilian sample), evaluating their effectiveness. Results: The study sample included 22,562 individuals (19,069 from Brazil, and 3,493 from Spain). The models developed performed similarly and were equally effective in predicting depression and anxiety in both tests, with internal test AUC-ROC values of 0.85 (depression) and 0.86 (anxiety), and external test AUC-ROC values of 0.85 (depression) and 0.84 (anxiety). Meaning of life was the strongest predictor of depression, while sleep quality was the strongest predictor of anxiety during the COVID-19 epidemic. Conclusions: Specific lifestyle behaviors during the early COVID-19 epidemic successfully predicted the presence of depression and anxiety in a large Brazilian sample using machine learning models developed on a Spanish sample. Targeted interventions focused on promoting healthier lifestyles are encouraged. [ABSTRACT FROM AUTHOR]

Forest ecosystems are important in the carbon storage process. Thus, the objective was to investigate the effectiveness of the Simulated Annealing metaheuristic analysis for selecting variables to maximize the accuracy of the aboveground carbon prediction at the tree level. We used data from uneven-aged forests located in the Rio Grande Basin - Minas Gerais, Brazil, where 227 trees had their carbon stock measured. The classic Spurr linear model, stepwise linear regression and pan-tropical coverage, Random Forest (RF), and the hybrid SARF method (Simulated Annealing and Random Forest) were used to estimate the carbon stock from the selection of variables for the different compartments of the tree (total, stem, branch, and leaf). The SARF consisted of the metaheuristic to select the variables to be used in the RF. These methods were evaluated by the root mean square error (RMSE), coefficient of determination (R²), and residual graph. As a result, the pan-tropical equation demonstrated superior performance than the Spurr model due to its greater homogeneity of residues. The stepwise technique reduced the number of variables and the error of the estimates, mainly for the validation set. SARF showed better adjustments than RF, as it reduced in on average 99.2% of the number of variables and 9% of the error of estimates considering all compartments. In general, variables such as volume, basic wood density, canopy projection area, diameter at 0%, diameter at breast height, height, and latitude contributed strongly to the carbon independent of the tree compartment. Among the methods, SARF is an alternative to the traditional method, as it can extract accurate information from a large data set. [ABSTRACT FROM AUTHOR]

Dynamics studies associated with prognosis can support planning actions for the conservation and sustainable use of forest resources. Therefore, the objective of this study was to evaluate the dynamics and predict the diameter structure using the Markov chain model for an area of caatinga forest submitted to different management practices. The study was carried out in the Contendas do Sincorá National Forest in the state of Bahia. Four treatments were installed, corresponding to three management systems and one control. Data was obtained measuring all individuals with a diameter greater than or equal to 5 cm. The measurements were performed at two moments in 2015 and 2018. The results indicated that the selective cut-by-diameter treatment had the lowest mortality rate and the highest recruitment rate. Predictions of the diameter structure using the Markov chain do not generally present statistical differences (α0.01) between the observed and expected frequencies for the year 2018. It was concluded that the basal area showed a tendency for recovery and growth in the treatments which involved suppression compared to the control, with no statistically significant differences among treatments until the moment after intervention. [ABSTRACT FROM AUTHOR]

We investigated how the potential distribution of Histiotus velatus is affected by the addition of new records over decades (decade effect). Assuming that (1: hypothesis of the effect of the decade) the addition of new occurrence records over time increases the potential size of the species distribution; and (2: Wallacean distance hypothesis) over the years, the new points added are increasingly distant from the research centers. Considering the geographic knowledge gap of this species, our objective is to report a new record of this species and estimate its potential distribution in South America through environment niche models (ENMs). For this, we compiled records of occurrence of species, selected from 1900 to 2015. We used 19 bioclimatic variables available in the WorldClim database to estimate the potential distribution of the species, and we used three modeling algorithms: Maximum Entropy (MXT), Random Forest (RDF), and Support Vector Machine. To test the Wallacean distance hypothesis, we calculated the Euclidian distance from occurrences to bat research centers in Brazil, located using a national researchers' information dataset ("Plataforma Lattes"). To test the hypothesis of the decade effect, we used the beta regression analysis, taking conservative and non‐conservative approaches. The results showed that the predicted area expanded and retracted with the addition of new occurrences over the decades, with an improvement in the accuracy of models. Most records are located in the southeastern region of Brazil, but algorithms predicted areas in regions where there are no records. Only the conservative approach has had a positive relationship over the decades. The distance from new points does not increase over the years of research centers. [ABSTRACT FROM AUTHOR]

The complexity and practical importance of insect outbreaks have made the problem of predicting outbreaks a focus of recent research. We propose the Pattern-Based Prediction (PBP) method for predicting population outbreaks. It uses information on previous time series values that precede an outbreak event as predictors of future outbreaks, which can be helpful when monitoring pest species. We illustrate the methodology using simulated datasets and an aphid time series obtained in wheat crops in Southern Brazil. We obtained an average test accuracy of 84.6 % in the simulation studies implemented with stochastic models and 95.0 % for predicting outbreaks using a time series of aphids in wheat crops in Southern Brazil. Our results show the PBP method's feasibility in predicting population outbreaks. We benchmarked our results against established state-of-the-art machine learning methods: Support Vector Machines, Deep Neural Networks, Long Short Term Memory and Random Forests. The PBP method yielded a competitive performance associated with higher true-positive rates in most comparisons while providing interpretability rather than being a black-box method. It is an improvement over current state-of-the-art machine learning tools, especially by non-specialists, such as ecologists aiming to use a quantitative approach for pest monitoring. We provide the implemented PBP method in Python through the pypbp package. • We propose the Pattern-Based Prediction (PBP) method for predicting population outbreaks. • We illustrate the methodology using simulated datasets and an time series of aphid counts in wheat crops in Southern Brazil. • Our results show the PBP method's feasibility in predicting population outbreaks. • The PBP method yielded a competitive performance while providing interpretability rather than being a black-box method. • We provide the implemented PBP method in Python through the pypbp package. [ABSTRACT FROM AUTHOR]

Following the Fund ão dam failure in Brazil, 60 million m3 of iron-rich tailings were released impacting an extensive area. After this catastrophe, a detailed characterization and monitoring of iron-rich tailings is required for agronomic and environmental purposes. This can be facilitated by using proximal sensors which have been an efficient, fast, and cost-effective tool for eco-friendly analysis of soils and sediments. This work hypothesized that portable X-ray fluorescence (pXRF) spectrometry combined with a pocket-sized (Nix™ Pro) color sensor and benchtop magnetic susceptibilimeter can produce substantial data for fast and clean characterization of iron-rich tailings. The objectives were to differentiate impacted and non-impacted areas (soils and sediments) based on proximal sensors data, and to predict attributes of agronomic and environmental importance. A total of 148 composite samples were collected on totally impacted, partially impacted, and non-impacted areas (natural soils). The samples were analyzed via pXRF to obtain the total elemental composition; via Nix™ Pro color sensor to obtain the red (R), green (G), and blue (B) parameters; and assessed for magnetic susceptibility (MS). The same samples used for analyses via the aforementioned sensors were wet-digested (USEPA 3051a method) followed by ICP-OES quantification of potentially toxic elements. Principal component analysis was performed to differentiate impacted and non-impacted areas. The pXRF data alone or combined with other sensors were used to predict soil agronomic properties and semi-total concentration of potentially toxic elements via random forest regression. For that, samples were randomly separated into modeling (70%) and validation (30%) datasets. The pXRF proved to be an efficient method for rapid and eco-friendly characterization of iron-rich tailings, allowing a clear differentiation of impacted and non-impacted areas. Also, important soil agronomic properties (clay, cation exchange capacity, soil organic carbon, pH and macronutrients availability) and semi-total concentrations of Ba, Pb, Cr, V, Cu, Co, Ni, Mn, Ti, and Li were accurately predicted (based upon the lowest RMSE and highest R2 and RPD values). Sensor data fusion (pXRF + Nix Pro + MS) slightly improved the accuracy of predictions. This work highlights iron-rich tailings from the Fund ão dam failure can be in detail characterized via pXRF ex situ , providing a secure basis for complementary studies in situ aiming at identify contaminated hot spots, digital mapping of soil and properties variability, and embasing pedological, agricultural and environmental purposes. • pXRF data and random forest algorithm accurately predicted iron-rich tailings properties. • Potentially toxic elements (Ba, Pb, Cr, V, Cu, Co, and Ni) were successfully predicted. • Soil agronomic properties were also accurately predicted with high R2 values. • These findings constitute a secure dataset for environmental recomposition planning. [ABSTRACT FROM AUTHOR]

• Machine learning and geostatistical models for soil mapping. • Relationship between soil fertility and environmental/management covariates. • A trade off between spatial cover grids and sample planning optimization. • The benefits of using covariates in sample optimization depend on field management. • As higher the knowledge about field variability, the more accurate is the optimization. The study aimed to evaluate whether the use of covariates in sample optimization helps characterize the spatial variability of soil chemical properties. To this end, data from two agricultural areas located in southeastern Brazil were used. The covariates were used at two stages: sample planning optimization and building predictive methods. The covariates were divided into five categories: relief, vegetation, soil, management, and spatial coordinates. We compared two criteria in sample planning optimization: one aims to ensure spatial distribution by minimizing the mean squared shortest distance (MSSD); the other integrated four criteria through a multipurpose function (SPAN), aiming to represent the distribution and correlation between the covariates, the minimization of the mean squared shortest distance and the distribution of pairs of points for each lag size of the semivariogram. We evaluated three predictive methods (Robust Ordinary Kriging (ROK), Random Forest (RF), and Random Forest-Robust Kriging (RF-RK)) and a null model (mean-based) to predict four soil properties (Cation exchange capacity (CEC), Base saturation (V), Potassium (K) and Phosphorus (P)). We observed that not all areas would benefit from the inclusion of covariates in the sample planning. When our previous knowledge of variability is limited or unknown, we need to evaluate the management in the areas. When the cropping system is more complex and diversified, spatial coverage sampling is more feasible, using the covariates only on the prediction models. [ABSTRACT FROM AUTHOR]

The Famacha© method has been created for detecting sheep unable to cope with the infection by Haemonchus contortus, through visual assessment of ocular conjunctiva coloration. The objective of this study was to develop a computer vision system (CVS) for prediction of Famacha© degree (FAM) from ocular conjunctiva images. The dataset consisted of 475 ocular conjunctiva images from animals in two farms. A Random Forest (RF) approach was used to segment the images, i.e. to select the pixels that belong to the ocular conjunctiva. After segmentation, the quantiles (0, 25, 50, 75, and 100%) of color intensity in each channel (red, blue, and green) were determined and used in multinomial logistic regression and RF models to classify the animals according to FAM. The classification methods were fitted using the information of quantiles, and the FAM (scores 1 to 5, non-anemic to severely anemic, respectively) as the target classes to be predicted. The RF presented the best performance in predicting degrees 1 to 4, with an F1 score, that represents the balance between the precision and the recall, of 50.0% for degree 1, 72.7% for degree 2, 75.4% for degree 3, and 62.2% for degree 4, where degrees 3 and 4 refer to animals that need treatment. None of the two prediction approaches were able to satisfactorily classify degree 5 animals. The results suggest that it is feasible to adequately predict the FAM in real-time from images of the conjunctiva ocular in sheep, providing key information for management decisions on the farm. Nonetheless, further studies and larger datasets may be needed to increase the classification accuracy of degree 5 animals. In conclusion, it was demonstrated that it is possible to successfully predict degrees of Famacha 1 to 4 in sheep via CVS using images collected in farm conditions. Supported by the São Paulo Research Foundation (FAPESP) grants #2020/03575-8, #2018/01540-2 and #2016/14522-7, Brazil. [ABSTRACT FROM AUTHOR]

Information on vegetation height can be used in a variety of applications, but the high cost to obtain it in large areas using field sampling and the latest remote sensing technologies is still a barrier for low-income countries and organizations. In an attempt to overcome these limitations, we explored the possibility to estimate vegetation height in fragments of Atlantic Forest (São Paulo - Brazil) based on Sentinel 2 imagery, using LiDAR (Light Detection And Ranging) and field data as reference. The initial results showed that only wet season images appear to be related to the vegetation height, especially band 5 (red-edge) and related vegetation indices (VIs). Predictions made with Sentinel 2 and LiDAR data showed that vegetation height can be estimated with a root mean square error (RMSE) close to 3 m, with simple linear models outperforming random forest algorithms. It's also shown in a variety of validation tests, that although better results are obtained if the models are applied to the same images they were trained in, they are still able to reasonably predict vegetation height when applied to other images and locations if the right predictive variables are used. The results agree with recent studies made in other biomes and show that Sentinel 2 imagery can be used to estimate vegetation height in the Atlantic Forest as well. We conclude that vegetation height estimates with linear models can be used as a simple low cost alternative for future applications in this environment. [Display omitted] • Regression models with Sentinel 2 data were created to estimate vegetation height. • Vegetation height was more strongly related to visible and red-edge wavelengths. • Linear models could predict vegetation height with mean errors close to 3 m. • Only level-2A wet season images seem appropriate to make predictions. • Sentinel 2 may optimize and reduce costs of large area vegetation height sampling. [ABSTRACT FROM AUTHOR]

Despite being a very common phenomenon worldwide, in Brazil, the factors and mechanisms that control gully erosion on a regional scale are still little known, which leads to the neglect of this environmental hazard by territorial and environmental management policies. In order to reducing this gap, we explored the potential of four common supervised machine learning algorithms, named random forest (RF), logistic regression (LR), naïve Bayes (NB) and artificial neural network (ANN) to produce gully erosion susceptibility models for two gullied watersheds, located in the state of Minas Gerais, southeastern Brazil. The modeling was based on the construction of a solid gully inventory and a database consisting of fifteen geo-environmental factors (GEF), whose influence was determined from the information gain ratio (IGR) and two bivariate statistical methods, named frequency ratio (FR) and modified information value (MIV). The predictive performance of the models was evaluated by the area under the receiver operating characteristic curve (AUC), overall accuracy (ACC) and sufficiency analysis. The results revealed that random forest achieved the highest overall performance in correct prediction of gullies and produced the most realistic gully susceptibility maps. The IGR data indicated that all GEF considered in the analysis contributed to the predictive model, although lithology, elevation and rainfall are the most influential variables. From an integrated analysis between the gully inventory, field observations, FR and MIV values, we found that gullies seem to be triggered by high annual average rainfall, but only develop where a set of specific geo-environmental conditions occur simultaneously. Finally, despite the limited land use data available, anthropogenic activities do not seem to affect the regional distribution pattern of gullies, although we have not excluded their local influence in triggering some erosive features. [Display omitted] • Random Forest achieved the best performance in gully prediction. • Gully erosion develops where a set of specific conditions occur simultaneously. • Lithology, elevation and rainfall control gully distribution in the study area. • Anthropogenic activities do not seem to affect the regional gully distribution. [ABSTRACT FROM AUTHOR]

The health sector faces a series of problems generated by patients who miss their scheduled appointments. The main challenge to this problem is to understand the patient's profile and predict potential absences. The goal of this work is to explore the main causes that contribute to a patient's no-show and develop a prediction model able to identify whether the patient will attend their scheduled appointment or not. The study was based on data from clinics that serve the Unified Health System (SUS) at the University of Vale do Itajaí in southern Brazil. The model obtained was tested on a real collected dataset with about 5000 samples. The best model result was performed by the Random Forest classifier. It had the best Recall Rate (0.91) and achieved an ROC curve rate of 0.969. This research was approved and authorized by the Ethics Committee of the University of Vale do Itajaí, under opinion 4270,234, contemplating the General Data Protection Law. [ABSTRACT FROM AUTHOR]

Simple Summary: Monitoring animal activity in production systems is an important tool for obtaining information on health, production, and reproduction. In this study, we evaluated the use of accelerometers with different strategies to predict the grazing behavior of Nelore cattle. This research was conducted in an environment both more challenging and representative of the practices adopted in livestock production systems in Brazil. The results of this study showed that the use of the Random Forest algorithm, together with techniques for resampling the training data of the models, classified the studied behaviors with high accuracy, especially for important, and less frequent activities such as water consumption frequency. Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest. [ABSTRACT FROM AUTHOR]

Ethanol is one of the most used fuels in Brazil, which is the second-largest producer of this biofuel in the world. The uncertainty of price direction in the future increases the risk for agents operating in this market and can affect a dependent price chain, such as food and gasoline. This paper uses the architecture of recurrent neural networks—Long short-term memory (LSTM)—to predict Brazilian ethanol spot prices for three horizon-times (12, 6 and 3 months ahead). The proposed model is compared to three benchmark algorithms: Random Forest, SVM Linear and RBF. We evaluate statistical measures such as MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and accuracy to assess the algorithm robustness. Our findings suggest LSTM outperforms the other techniques in regression, considering both MSE and MAPE but SVM Linear is better to identify price trends. Concerning predictions per se, all errors increase during the pandemic period, reinforcing the challenge to identify patterns in crisis scenarios. [ABSTRACT FROM AUTHOR]