Search

Late leaf spot (LLS) is an important disease of peanut, causing global yield losses. Developing resistant varieties through breeding is crucial for yield stability, especially for smallholder farmers. However, traditional phenotyping methods used for resistance selection are laborious and subjective. Remote sensing offers an accurate, objective, and efficient alternative for phenotyping for resistance. The objectives of this study were to compare between regression and classification for breeding, and to identify the best models and indices to be used for selection. We evaluated 223 genotypes in three environments: Serere in 2020, and Nakabango and Nyankpala in 2021. Phenotypic data were collected using visual scores and two handheld sensors: a red–green–blue (RGB) camera and GreenSeeker. RGB indices derived from the images, along with the normalized difference vegetation index (NDVI), were used to model LLS resistance using statistical and machine learning methods. Both regression and classification methods were also evaluated for selection. Random Forest (RF), the artificial neural network (ANN), and k-nearest neighbors (KNNs) were the top-performing algorithms for both regression and classification. The ANN (R2: 0.81, RMSE: 22%) was the best regression algorithm, while the RF was the best classification algorithm for both binary (90%) and multiclass (78% and 73% accuracy) classification. The classification accuracy of the models decreased with the increase in classification classes. NDVI, crop senescence index (CSI), hue, and greenness index were strongly associated with LLS and useful for selection. Our study demonstrates that the integration of remote sensing and machine learning can enhance selection for LLS-resistant genotypes, aiding plant breeders in managing large populations effectively. [ABSTRACT FROM AUTHOR]

Agricultural intensification practices have been adopted in the Brazilian savanna (Cerrado), mainly in the transition between Cerrado and the Amazon Forest, to increase productivity while reducing pressure for new land clearing. Due to the growing demand for more sustainable practices, more accurate information on geospatial monitoring is required. Remote sensing products and artificial intelligence models for pixel-by-pixel classification have great potential. Therefore, we developed a methodological framework with spectral indices (Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Soil-Adjusted Vegetation Index (SAVI)) derived from the Harmonized Landsat Sentinel-2 (HLS) and machine learning algorithms (Random Forest (RF), Artificial Neural Networks (ANNs), and Extreme Gradient Boosting (XGBoost)) to map agricultural intensification considering three hierarchical levels, i.e., temporary crops (level 1), the number of crop cycles (level 2), and the crop types from the second season in double-crop systems (level 3) in the 2021–2022 crop growing season in the municipality of Sorriso, Mato Grosso State, Brazil. All models were statistically similar, with an overall accuracy between 85 and 99%. The NDVI was the most suitable index for discriminating cultures at all hierarchical levels. The RF-NDVI combination mapped best at level 1, while at levels 2 and 3, the best model was XGBoost-NDVI. Our results indicate the great potential of combining HLS data and machine learning to provide accurate geospatial information for decision-makers in monitoring agricultural intensification, with an aim toward the sustainable development of agriculture. [ABSTRACT FROM AUTHOR]

Corn and soybeans are crucial crops for feeding the world's population, and it is essential to monitor and map these fields for effective agricultural planning. With recent advancements in remote sensing technology and deep learning algorithms, more intelligent management of these crops has become possible. In this paper, we compare modern deep learning (DL) architectures for mapping corn and soybean crops in the state of Iowa, in United States of America (USA), using temporal Landsat 8 (OLI) images. Our analysis focuses on the performance of six different DL networks, namely 1-D CNN, 1-D CNN-LSTM, 2-D UNet, 2D UNet 3+, 2D Attention UNet, and 2D Recurrent Residual UNet. For each network, we use time-series Normalized Difference Vegetation Index (NDVI) data derived from Landsat 8 images taken between April and November 2020 as input, while ground truth labels are taken from the United States Department of Agriculture (USDA). Our experimental results show that the 2-D Recurrent Residual U-net model achieved the highest accuracy for identifying corn and soybean classes, with an Fscore of 92.85. This indicates the model's ability to distinguish complex features and patterns with similar spectral characteristics from multi-temporal remote sensing data. Conversely, the CNN and CNN-LSTM models had the worst performance among the considered models, with an F-score of about 89.50. Nevertheless, all the DL methods examined in this study achieved acceptable classification kappa coefficients (above 82%), indicating their significant potential for accurately mapping and monitoring Corn and Soybean crops. [ABSTRACT FROM AUTHOR]

Predicting groundwater levels is challenging, especially in regions of water scarcity where data availability is often limited. However, these regions have substantial water needs and require cost-effective groundwater utilization strategies. This study uses artificial intelligence to predict groundwater levels to provide guidance for drilling shallow boreholes for subsistence irrigation. The Bilate watershed, located 80 km north of Arba Minch in southern Ethiopia and covering just over 5250 km2, was selected as the study area. Bilate is typical of areas in Africa with high demand for water and limited availability of well data. Using a non-time series database of 75 boreholes, machine learning models, including multiple linear regression, multivariate adaptive regression splines, artificial neural networks, random forest regression, and gradient boosting regression (GBR), were constructed to predict the depth to the water table. The study considered 20 independent variables, including elevation, soil type, and seasonal data (spanning three seasons) for precipitation, specific humidity, wind speed, land surface temperature during day and night, and Normalized Difference Vegetation Index (NDVI). GBR performed the best of the approaches, with an average 0.77 R-squared value and a 19 m median absolute error on testing data. Finally, a map of predicted water levels in the Bilate watershed was created based on the best model, with water levels ranging from 1.6 to 245.9 m. With the limited set of borehole data, the results show a clear signal that can provide guidance for borehole drilling decisions for sustainable irrigation with additional implications for drinking water. [ABSTRACT FROM AUTHOR]

The monitoring and determination of peanut maturity are fundamental to reducing losses during digging operation. However, the methods currently used are laborious and subjective. To solve this problem, we developed models to access peanut maturity using images from unmanned aerial vehicles (UAV) and satellites. We evaluated an area of approximately 8 hectares in which a regular grid of 30 points was determined with weekly evaluations starting at 90 days after sowing. Two Artificial Neural Networking (ANN) were used with Radial Basis Function (RBF) and Multilayer Perceptron (MLP) to predict the Peanut Maturity Index (PMI) with the spectral bands available from each sensor. Several vegetation indices were used as input to the ANN, with the data being split 80/20 for training and validation, respectively. The vegetation index, Normalized Difference Red Edge Index (NDRE), was the most precise coefficient of determination (R2 = 0.88) and accurate mean absolute error (MAE = 0.06) for estimating PMI, regardless of the type of ANN used. The satellite with Normalized Difference Vegetation Index (NDVI) could also determine PMI with better accuracy (MAE = 0.05) than the NDRE. The performance evaluation indicates that the RBF and MLP networks are similar in predicting peanut maturity. We concluded that satellite and UAV images can predict the maturity index with good accuracy and precision. [ABSTRACT FROM AUTHOR]

Short-range predictions of crop yield provide valuable insights for agricultural resource management and likely economic impacts associated with low yield. Such predictions are difficult to achieve in regions that lack extensive observational records. Herein, we demonstrate how a number of basic or readily available input data can be used to train an Artificial Neural Network (ANN) model to provide months-ahead predictions of cotton yield for a case study in Menemen Plain, Turkey. We use limited reported yield (13 years) along cumulative precipitation, cumulative heat units, two meteorologically-based drought indices (Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI)), and three remotely-sensed vegetation indices (Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Land Surface Water Index (LSWI)) as ANN inputs. Results indicate that, when EVI is combined with the preceding 12-month SPEI, it has better sensitivity to cotton yield than other indicators. The ANN model predicted cotton yield four months before harvest with R2 > 0.80, showing potential as a yield prediction tool. We discuss the effects of different combinations of input data (explanatory variables), dataset size, and selection of training data to inform future applications of ANN for early prediction of cotton yield in data-scarce regions. [ABSTRACT FROM AUTHOR]

Mapping of groundwater distribution potential over space, built by synergizing environmental variables and machine learning models, was of great significance for regional water resources management. A total of 245 wells were identified based on field survey in the Chihe River basin in Anhui province, out of which 172 wells locations were randomly used for training the machine models and the other 73 wells for validation process of machine models. Thirteen environmental variables including elevation, slope, slope aspect, plan curvature, profile curvature, topographic wetness index (TWI), drainage density, distance to rivers, distance to faults, lithology, soil type, land use, and normalized difference vegetation index (NDVI) were used to build the spatial database of this research. Three GIS-based machine learning models were used for mapping the groundwater distribution potential: logistic regression (LR), deep neural networks (DNN) and random forest (RF). Then, the applicability of those models was evaluated by the evaluation index of mean absolute error (MAE), root mean square error (RMSE) and correlation coefficient (R). The final results indicated that the potential of regional groundwater distribution is concentrated in moderate to high potential areas. Among them, the moderate to the high potential distribution area in the LR model accounted for 81.14% of the total area, 90.36% and 87.55% in the DNN model and the RF model, respectively. In addition, three machine learning models can be implemented for prediction of groundwater distribution based on the three evaluation indexes, among which the LR model performs more prominently. The good prediction capabilities of machine learning technologies can provide a reliable scientific basis for spatial prediction of groundwater distribution and management of water resources. [ABSTRACT FROM AUTHOR]

• A bayesian neural network model predicts Canadian spring wheat yields. • Inputs to model includes NDVI anomalies and drought assessments. • The model predicts yield with errors ranging from 13% to 18% of mean yields. • Model can be used with drought assessments to understand impact of drought hazards on risks to crop yields. The Canadian drought monitor (CDM) provides monthly assessments of drought severity but does not provide guidance on the potential agricultural impacts. This study extends the CDM to a comprehensive risk assessment framework by assessing the vulnerability of spring wheat to drought timing and severity in the Canadian Prairies. To achieve this, a bayesian neural network (BNN) model was developed that predicts high-resolution wheat yields and uncertainties using the CDM and normalized difference vegetation index (NDVI) data from 2010 to 2021. Model performance is comparable to previous studies, with errors ranging from 13% to 18% of mean yields and R2 values from 0.43 to 0.70 that peak in early August. The model was then applied under various drought conditions to evaluate how different drought timings and severities affect yield vulnerability. The results demonstrate that drought exposure from June to August reduces wheat yields in proportion to drought severity while abnormally dry conditions may have a positive impact of yield, particularly in August. Yield uncertainty decreases substantially from June to July while yield prediction accuracy increases, suggesting that mitigation efforts are most effective prior to July. The final component of the research involved creating operational risk maps that integrate the yield vulnerability assessment with the CDM. These maps were applied in a case study to demonstrate their utility in providing actionable, real-time information for agricultural stakeholders. Overall, this study contributes to the body of knowledge regarding crop sensitivities to varying drought conditions and represents a methodological advancement by enabling high-resolution, operational agricultural risk assessments at scale. By integrating detailed vulnerability data with drought hazard monitoring from the CDM, the information provided by these risk maps can be leveraged by agricultural stakeholders in near real-time to make well-informed decisions that mitigate the impacts of drought on wheat production, enhancing the resilience of agricultural systems to climatic variability. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) remote sensing technology can be used for fast and efficient monitoring of plant diseases and pests, but these techniques are qualitative expressions of plant diseases. However, the yellow leaf disease of arecanut in Hainan Province is similar to a plague, with an incidence rate of up to 90% in severely affected areas, and a qualitative expression is not conducive to the assessment of its severity and yield. Additionally, there exists a clear correlation between the damage caused by plant diseases and pests and the change in the living vegetation volume (LVV). However, the correlation between the severity of the yellow leaf disease of arecanut and LVV must be demonstrated through research. Therefore, this study aims to apply the multispectral data obtained by the UAV along with the high-resolution UAV remote sensing images to obtain five vegetation indexes such as the normalized difference vegetation index (NDVI), optimized soil adjusted vegetation index (OSAVI), leaf chlorophyll index (LCI), green normalized difference vegetation index (GNDVI), and normalized difference red edge (NDRE) index, and establish five algorithm models such as the back-propagation neural network (BPNN), decision tree, naïve Bayes, support vector machine (SVM), and k-nearest-neighbor classification to determine the severity of the yellow leaf disease of arecanut, which is expressed by the proportion of the yellowing area of a single areca crown (in percentage). The traditional qualitative expression of this disease is transformed into the quantitative expression of the yellow leaf disease of arecanut per plant. The results demonstrate that the classification accuracy of the test set of the BPNN algorithm and SVM algorithm is the highest, at 86.57% and 86.30%, respectively. Additionally, the UAV structure from motion technology is used to measure the LVV of a single areca tree and establish a model of the correlation between the LVV and the severity of the yellow leaf disease of arecanut. The results show that the relative root mean square error is between 34.763% and 39.324%. This study presents the novel quantitative expression of the severity of the yellow leaf disease of arecanut, along with the correlation between the LVV of areca and the severity of the yellow leaf disease of arecanut. Significant development is expected in the degree of integration of multispectral software and hardware, observation accuracy, and ease of use of UAVs owing to the rapid progress of spectral sensing technology and the image processing and analysis algorithms. [ABSTRACT FROM AUTHOR]

Ecosystems, settlements, and human lives are put at risk by forest fires every year. Several models proposed for the prediction of their occurrence and behavior have aimed at identifying their conditioning factors, risks, and post-effects. However, their application in other regions is impracticable or very difficult, due to the distinct geographic characteristics of the areas and the unavailability of data. This research is devoted to the prediction of both spread and behavior of wildfires at a specific time and/or in specific regions for helping fire management agencies minimize the damages caused. The Brazilian Federal District, inserted in the Cerrado biome, is the focus of the analyses, due to its large number of fire occurrences and reduced number of studies conducted on the region. A dataset was compiled from Brazilian governmental open data for the prediction of the wildfire behavior and used for the training of several Machine Learning models that consider the fire point of ignition to predict the areas that will be impacted. It includes observations on climate features from 5 monitoring stations and satellite data on fires that occurred over the past two decades and was enriched with other topographic, hydrographic, and anthropogenic features, such as urbanization index, distance to rivers/roads, and Normalized Difference Vegetation Index (NDVI). According to the results, AdaBoost model predicted the area affected by the wildfire with 91% accuracy, showing better performance than Random Forest (RF) 88%, Artificial Neural Network (ANN) 86%, and Support Vector Machine (SVM) 81%. [ABSTRACT FROM AUTHOR]

Urban flooding is a devastating natural hazard for cities around the world. Flood risk mapping is a key tool in flood management. However, it is computationally expensive to produce flood risk maps using hydrodynamic models. To this end, this paper investigates the use of machine learning for the assessment of surface water flood risks in urban areas. The factors that are considered in machine learning models include coordinates, elevation, slope gradient, imperviousness, land use, land cover, soil type, substrate, distance to river, distance to road, and normalized difference vegetation index. The machine learning models are tested using the case study of Exeter, UK. The performance of machine learning algorithms, including naïve Bayes, perceptron, artificial neural networks (ANNs), and convolutional neural networks (CNNs), is compared based on a spectrum of indicators, e.g., accuracy, F-beta score, and receiver operating characteristic curve. The results obtained from the case study show that the flood risk maps can be accurately generated by the machine learning models. The performance of models on the 30-year flood event is better than 100-year and 1000-year flood events. The CNNs and ANNs outperform the other machine learning algorithms tested. This study shows that machine learning can help provide rapid flood mapping, and contribute to urban flood risk assessment and management. [ABSTRACT FROM AUTHOR]