Search Results (2,590)

Artificial Intelligence (AI) has changed how processes are developed, and decisions are made in the agricultural area replacing manual and repetitive processes with automated and more efficient ones. This study presents the application of deep learning techniques to detect and segment weeds in agricultural crops by applying models with different architectures in the analysis of images captured by an Unmanned Aerial Vehicle (UAV). This study contributes to the computer vision field by comparing the performance of the You Only Look Once (YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l), Mask R-CNN (with framework Detectron2), and U-Net models, making public the dataset with aerial images of soybeans and beans. The models were trained using a dataset consisting of 3021 images, randomly divided into test, validation, and training sets, which were annotated, resized, and increased using the Roboflow application interface. Evaluation metrics were used, which included training efficiency (mAP50 and mAP50-90), precision, accuracy, and recall in the model’s evaluation and comparison. The YOLOv8s variant achieved higher performance with an mAP50 of 97%, precision of 99.7%, and recall of 99% when compared to the other models. The data from this manuscript show that deep learning models can generate efficient results for automatic weed detection when trained with a well-labeled and large set. Furthermore, this study demonstrated the great potential of using advanced object segmentation algorithms in detecting weeds in soybean and bean crops. Full article

The integration of the Crop Growth Model (CGM), Radiative Transfer Model (RTM), and Machine Learning Algorithm (MLA) for estimating crop traits represents a cutting-edge area of research. This integration requires in-depth study to address RTM limitations, particularly of similar spectral responses from multiple input combinations. This study proposes the integration of CGM and RTM for crop trait retrieval and evaluates the performance of CGM output-based RTM spectra generation for multiple crop traits estimation without biased sampling using machine learning models. Moreover, PROSAIL spectra as training against Harmonized Landsat Sentinel-2 (HLS) as testing was also compared with HLS data only as an alternative. It was found that satellite data (HLS, 80:20) not only consistently performed better, but PROSAIL (train) and HLS (test) also had satisfactory results for multiple crop traits from uniform training samples in spite of differences in simulated and real data. PROSAIL-HLS has an RMSE of 0.67 for leaf area index (LAI), 5.66 µg/cm² for chlorophyll ab (Cab), 0.0003 g/cm² for dry matter content (Cm), and 0.002 g/cm² for leaf water content (Cw) against the HLS only, with an RMSE of 0.40 for LAI, 3.28 µg/cm² for Cab, 0.0002 g/cm² for Cm, and 0.001 g/cm² for Cw. Optimized machine learning models, namely Extreme Gradient Boost (XGBoost) for LAI, Support Vector Machine (SVM) for Cab, and Random Forest (RF) for Cm and Cw, were deployed for temporal mapping of traits to be used for wheat productivity enhancement. Full article

The study, carried out as part of the International Cooperative Program on Effects of Air Pollution on Natural Vegetation and Crops, involved collecting 95 moss samples across the territory of Georgia during the period from 2019 to 2023. Primarily samples of Hypnum cupressiforme were selected, with supplementary samples of Abietinella abietina, Pleurozium schreberi, and Hylocomium splendens in cases of the former’s absence. The content of 14 elements (Al, Ba, Cd, Co, Cr, Cu, Fe, Mn, Ni, Pb, S, Sr, V, and Zn) was detected using Inductively Coupled Plasma Atomic Emission Spectroscopy (ICP-AES), while the Hg content was determined using a Direct Mercury Analyzer. To identify any relationships between chemical elements and to depict their sources, multivariate statistics was applied. Principal component analysis identified three main components: PC1 (geogenic, 43.4%), PC2 (anthropogenic, 13.3%), and PC3 (local anomalies, 8.5%). The results were compared with the first moss survey conducted in Georgia in the period from 2014 to 2017, offering insights into temporal trends of air quality. Utilizing GIS, a spatial map illustrating pollution levels across Georgia, based on the Pollution Load Index, was generated. The Potential Environmental Risk Index emphasized significant risks associated with mercury and cadmium at several locations. The study highlights the utility of moss biomonitoring in assessing air pollution and identifying hotspots of contamination. The findings from this study could be beneficial for future biomonitoring research in areas with varying physical and geographical conditions. Full article

Rice tiller angle is a key agronomic trait that regulates plant architecture and plays a critical role in determining rice yield. Given that tiller angle is regulated by multiple genes, it is important to identify quantitative trait loci (QTL) associated with tiller angle. Recently, with the advancement of imaging technology for plant phenotyping, it has become possible to quickly and accurately measure agronomic traits of breeding populations. In this study, we extracted tiller angle and various image-based parameters from Red-Green-Blue (RGB) images of a recombinant inbred line (RIL) population derived from a cross between Milyang23 (Indica) and Giho (Japonica). Correlations among the obtained data were analyzed, and through dynamic QTL mapping, five major QTLs (qTA1, qTA1-1, qTA2, qTA2-1, and qTA9) related to tiller angle were detected on chromosomes 1, 2, and 9. Among them, 26 candidate genes related to auxin signaling and plant growth, including the TAC1 (Tiller Angle Control 1) gene, were identified in qTA9 (RM257-STS09048). These results demonstrate the potential of image-based phenotyping to overcome the limitations of traditional manual measurements in crop structure research. Furthermore, the identification of key QTLs and candidate genes related to tiller angle provides valuable genetic insights for the development of high-yielding varieties through crop morphology control. Full article

High-resolution images captured by Unmanned Aerial Vehicles (UAVs) play a vital role in precision agriculture, particularly in evaluating crop health and detecting weeds. However, the detailed pixel information in these images makes classification a time-consuming and resource-intensive process. Despite these challenges, UAV imagery is increasingly utilized for various agricultural classification tasks. This study introduces an automatic classification method designed to streamline the process, specifically targeting cassava plants, weeds, and soil classification. The approach combines K-means unsupervised classification with spectral trend-based labeling, significantly reducing the need for manual intervention. The method ensures reliable and accurate classification results by leveraging color indices derived from RGB data and applying mean-shift filtering parameters. Key findings reveal that the combination of the blue (B) channel, Visible Atmospherically Resistant Index (VARI), and color index (CI) with filtering parameters, including a spatial radius (sp) = 5 and a color radius (sr) = 10, effectively differentiates soil from vegetation. Notably, using the green (G) channel, excess red (ExR), and excess green (ExG) with filtering parameters (sp = 10, sr = 20) successfully distinguishes cassava from weeds. The classification maps generated by this method achieved high kappa coefficients of 0.96, with accuracy levels comparable to supervised methods like Random Forest classification. This technique offers significant reductions in processing time compared to traditional methods and does not require training data, making it adaptable to different cassava fields captured by various UAV-mounted optical sensors. Ultimately, the proposed classification process minimizes manual intervention by incorporating efficient pre-processing steps into the classification workflow, making it a valuable tool for precision agriculture. Full article

Leaf nitrogen content (LNC) is a vital agronomic parameter in rice, commonly used to evaluate photosynthetic capacity and diagnose crop nutrient levels. Nitrogen deficiency can significantly reduce yield, underscoring the importance of accurate LNC estimation for practical applications. This study utilizes hyperspectral UAV imagery to acquire rice canopy data, applying various machine learning regression algorithms (MLR) to develop an LNC estimation model and create a nitrogen concentration distribution map, offering valuable guidance for subsequent field nitrogen management. The analysis incorporates four types of spectral data extracted throughout the rice growth cycle: original reflectance bands (OR bands), vegetation indices (VIs), first-derivative spectral bands (FD bands), and hyperspectral variable parameters (HSPs) as model inputs, while measured nitrogen concentration serves as the output. Results demonstrate that the random forest regression (RFR) and gradient boosting decision tree (GBDT) algorithms performed effectively, with the GBDT achieving the highest average R² of 0.76 across different nitrogen treatments. Among the nitrogen estimation models for various rice varieties, RFR exhibited superior accuracy, achieving an R² of 0.95 for the SuXiangJing100 variety, while the GBDT reached 0.93. Meanwhile, the support vector machine regression (SVMR) showed slightly lower accuracy, and partial least-squares regression (PLSR) was the least effective. This study developed an LNC estimation method applicable to the whole growth stage of common rice varieties. The method is suitable for estimating rice LNC across different growth stages, varieties, and nitrogen treatments, and it also provides a reference for nitrogen estimation and fertilization planning at flight altitudes other than the 120 m used in this study. Full article

In the face of growing challenges in modern agriculture, such as climate change, sustainable resource management, and food security, drones are emerging as essential tools for transforming precision agriculture. This systematic review, based on an in-depth analysis of recent scientific literature (2020–2024), provides a comprehensive synthesis of current drone applications in the agricultural sector, primarily focusing on studies from this period while including a few notable exceptions of particular interest. Our study examines in detail the technological advancements in drone systems, including innovative aerial platforms, cutting-edge multispectral and hyperspectral sensors, and advanced navigation and communication systems. We analyze diagnostic applications, such as crop monitoring and multispectral mapping, as well as interventional applications like precision spraying and drone-assisted seeding. The integration of artificial intelligence and IoTs in analyzing drone-collected data is highlighted, demonstrating significant improvements in early disease detection, yield estimation, and irrigation management. Specific case studies illustrate the effectiveness of drones in various crops, from viticulture to cereal cultivation. Despite these advancements, we identify several obstacles to widespread drone adoption, including regulatory, technological, and socio-economic challenges. This study particularly emphasizes the need to harmonize regulations on beyond visual line of sight (BVLOS) flights and improve economic accessibility for small-scale farmers. This review also identifies key opportunities for future research, including the use of drone swarms, improved energy autonomy, and the development of more sophisticated decision-support systems integrating drone data. In conclusion, we underscore the transformative potential of drones as a key technology for more sustainable, productive, and resilient agriculture in the face of global challenges in the 21st century, while highlighting the need for an integrated approach combining technological innovation, adapted policies, and farmer training. Full article

Heavy metal pollution is one of the most devastating abiotic factors, significantly damaging crops and human health. One of the serious problems it causes is a rise in cadmium (Cd) toxicity. Cd is a highly toxic metal with a negative biological role, and it enters plants via the soil–plant system. Cd stress induces a series of disorders in plants’ morphological, physiological, and biochemical processes and initiates the inhibition of seed germination, ultimately resulting in reduced growth. Fiber crops such as kenaf, jute, hemp, cotton, and flax have high industrial importance and often face the issue of Cd toxicity. Various techniques have been introduced to counter the rising threats of Cd toxicity, including reducing Cd content in the soil, mitigating the effects of Cd stress, and genetic improvements in plant tolerance against this stress. For decades, plant breeders have been trying to develop Cd-tolerant fiber crops through the identification and transformation of novel genes. Still, the complex mechanism of Cd tolerance has hindered the progress of genetic breeding. These crops are ideal candidates for the phytoremediation of heavy metals in contaminated soils. Hence, increased Cd uptake, accumulation, and translocation in below-ground parts (roots) and above-ground parts (shoots, leaves, and stems) can help clean agricultural lands for safe use for food crops. Earlier studies indicated that reducing Cd uptake, detoxification, reducing the effects of Cd stress, and developing plant tolerance to these stresses through the identification of novel genes are fruitful approaches. This review aims to highlight the role of some conventional and molecular techniques in reducing the threats of Cd stress in some key fiber crops. Molecular techniques mainly involve QTL mapping and GWAS. However, more focus has been given to the use of transcriptome and TFs analysis to explore the potential genomic regions involved in Cd tolerance in these crops. This review will serve as a source of valuable genetic information on key fiber crops, allowing for further in-depth analyses of Cd tolerance to identify the critical genes for molecular breeding, like genetic engineering and CRISPR/Cas9. Full article

Groundwater depletion in arid regions poses a significant threat to agricultural sustainability and rural livelihoods. This study employs geospatial analysis and economic modeling to address groundwater depletion in the arid Barind region of Northwest Bangladesh, where 84% of the rural population depends on agriculture. Using remote sensing and GIS, we developed an elevation map revealing areas up to 60 m above sea level, exacerbating evaporation and aquifer dryness. Field data collected through Participatory Rural Appraisal tools showed farmers exhibiting “ignorant myopic” behavior, prioritizing short-term profits over resource conservation. To address this, an Increasing Block Tariff (IBT) water pricing model was developed, dividing water usage into three blocks based on irrigation hours: 1–275 h, 276–550 h, and 551+ h. The proposed IBT model significantly increases water prices across the three blocks: 117 BDT/hour for the first block (from current 100–110 BDT/hour), 120 BDT/hour for the second block, and 138 BDT/hour for the third block. A demand function (y = −0.1178x + 241.8) was formulated to evaluate the model’s impact. The results show potential reductions in groundwater consumption: 59 h in the first block, 26 h in the second block, and 158 h in the third block. These reductions align with the principles of integrated water resource management (IWRM): social equity, economic efficiency, and environmental integration. The model incorporates economic externalities (e.g., well lifting costs) and environmental externalities (e.g., crop pattern shifts), with total costs reaching 92,709,049 BDT for environmental factors. This research provides a framework for sustainable groundwater management in arid regions, potentially reducing overextraction while maintaining agricultural productivity. The proposed IBT model offers a locally driven solution to balance resource conservation with the livelihood needs of farming communities in the Barind tract. By combining remote sensing, GIS, and economic modeling, this research provides a framework for sustainable groundwater management in arid regions, demonstrating the power of geospatial technologies in addressing complex water resource challenges. Full article

Weed canopy cover assessment, particularly using drone-acquired data, plays a vital role in precision agriculture by providing accurate, timely, and spatially detailed information, enhancing weed management decision-making in response to environmental and management variables. Despite the significance of this approach, few studies have investigated weed canopy cover through drone-based imagery. This study aimed to fill this gap by evaluating the effects of conventional tillage (CT) and no-till (NT) practices on weed canopy cover in a winter wheat field over two growing seasons. Results indicated that in the 2022–2023 season, weed populations were similar between tillage systems, with a high mean weed cover of 1.448 cm² ± 0.241 in CT plots. In contrast, during the 2023–2024 season, NT plots exhibited a substantially higher mean weed cover (1.784 cm² ± 0.167), with a significant overall variation (p < 0.05) in weed distribution between CT and NT plots. These differences suggest that, while CT practices initially mask weed emergence by burying seeds and disrupting root systems, NT practices encourage greater weed establishment over time by leaving seeds near the soil surface. These findings provide valuable insights for optimizing weed management practices, emphasizing the importance of comprehensive approaches to improve weed control and overall crop productivity. Full article

Mildew in maize kernels is typically caused by various fungi, necessitating prompt detection and treatment to minimize losses during harvest and storage. In this study, a deep learning YOLOv5s algorithm based on machine vision technology was employed to develop a maize seed surface mildew detection model and to enhance its portability for deployment on additional mobile devices. To guarantee the fruitful progression of this research, an initial experiment was conducted on maize seeds to obtain a sufficient number of images of mildewed maize kernels, which were classified into three grades (sound, mild, and severe). Subsequently, a maize seed image was extracted to create an image of a single maize seed, which was then divided to establish the data set. An enhanced YOLOv5s–ShuffleNet–CBAM model was ultimately developed. The results demonstrated that the model achieved with an mAP50 value of 0.955 and a model size of 2.4 MB. This resulted in a notable reduction in the model parameters and calculation amount while simultaneously enhancing model precision. Furthermore, K-fold cross-validation demonstrated the model stability, and Grad-CAM validated the model effectiveness. In the future, the proposed lightweight model in this study can be applied to other crops in the context of portable or online inspection systems, thus advancing effective and high-quality agricultural applications. Full article

The hypothesis of this study is that it is possible to determine the plant stand in the soybean (Glycine max L. Merril) crop based on the spatial variability of management units, which are limiting factors in maximizing crop yield. Our objectives were as follows: (I) to evaluate the relationship between soil physical and chemical attributes to establish potential management units for variable-rate seeding; (II) to propose a method for varying plant stands based on the law of minimum soil nutrients; an (III) to relate the interaction between different plant stands on soybean grain yield, taking into account the interaction between the spatial variability of the mapped attributes. Field experiments were carried out on two plots over two agricultural years. The areas were seeded by randomly varying the soybean stand across strips in the first year. The most limiting soil nutrient was established and used, together with the soil CEC, to determine management units (MUs), which were also used to seed soybeans in VRT (Variable Rate Technology) in the same plots in the second year. MUs with the lowest restriction for maximizing yield were sown in the second year with the lowest plant stand. Data were processed using multivariate statistics. Our findings reveal that it is possible to establish MUs for seeding soybeans with different stands following the spatial variability of limiting soil nutrients according to the law of the minimum and thus increase the crop grain yield. Spatial variability of potassium (K) in the plot, identified as limiting, affected the spatial variability of grain yield. Decreasing plant stands in MUs with the lowest limitation level increases yield. However, increasing the stand in MUs with a higher limitation level can lead to increased intraspecific competition, affecting yield as well as increasing input costs. Full article

The leaf morphology is an important agronomic trait in crop production. Our study identified a maple leaf type (mlt) cucumber mutant and located the regulatory gene for leaf shape changes through BSA results. Hybrid F1 and F2 populations were generated by F1 self-crossing, and the candidate mlt genes were identified within the 2.8 Mb region of chromosome 2 using map cloning. Through the sequencing and expression analysis of genes within the bulk segregant analysis (BSA) region, we identified the target gene for leaf shape regulation as CsWOX4 (CsaV3_2G026510). The change from base C to T in the original sequence led to frameshift mutations and the premature termination of translation, resulting in shortened encoded proteins and conserved WUSCHEL (WUS) box sequence loss. The specific expression analysis of the CsWOX4/Cswox4 genes in the roots, stems, leaves and other tissue types of wild-type (WT) and mutant plants revealed that CsWOX4 was higher in the root, but Cswox4 (mutant gene) was significantly higher in the leaf. Subcellular localization analysis revealed that CsWOX4 was localized in the nucleus. RNA-seq analysis revealed that the differentially expressed genes were mainly enriched in the mitochondrial cell cycle phase transition, nucleosome and microtubule binding pathways. Simultaneously, the quantitative analysis of the expression trends of 25 typical genes regulating the leaf types revealed the significant upregulation of CsPIN3. In our study, we found that the conserved domain of CsWOX4 was missing in the mutant, and the transcriptome data revealed that the expression of some genes, such as CsPIN3, changed simultaneously, thereby jointly regulating changes in the cucumber leaf type. Full article

Driven by the widespread adoption of deep learning (DL) in crop mapping with satellite image time series (SITS), this study was motivated by the recent success of temporal attention-based approaches in crop mapping. To meet the needs of beekeepers, this study aimed to develop DL-based classification models for mapping five essential crops in pollination services in Quebec province, Canada, by using Sentinel-2 SITS. Due to the challenging task of crop mapping using SITS, this study employed three DL-based models, namely one-dimensional temporal convolutional neural networks (CNNs) (1DTempCNNs), one-dimensional spectral CNNs (1DSpecCNNs), and long short-term memory (LSTM). Accordingly, this study aimed to capture expert-free temporal and spectral features, specifically targeting temporal features using 1DTempCNN and LSTM models, and spectral features using the 1DSpecCNN model. Our findings indicated that the LSTM model (macro-averaged recall of 0.80, precision of 0.80, F1-score of 0.80, and ROC of 0.89) outperformed both 1DTempCNNs (macro-averaged recall of 0.73, precision of 0.74, F1-score of 0.73, and ROC of 0.85) and 1DSpecCNNs (macro-averaged recall of 0.78, precision of 0.77, F1-score of 0.77, and ROC of 0.88) models, underscoring its effectiveness in capturing temporal features and highlighting its suitability for crop mapping using Sentinel-2 SITS. Furthermore, applying one-dimensional convolution (Conv1D) across the spectral domain demonstrated greater potential in distinguishing land covers and crop types than applying it across the temporal domain. This study contributes to providing insights into the capabilities and limitations of various DL-based classification models for crop mapping using Sentinel-2 SITS. Full article

Vegetable soybeans are one of the most important vegetable types in East Asia. The yield of vegetable soybeans is considerably influenced by the size of their pods. To facilitate the understanding of the genetic basis of the pod length and width in vegetable soybeans, we conducted a genome-wide association study (GWAS) and transcriptome sequencing. Four quantitative trait loci, namely, qGPoL1, qGPoL2, qGPoW1, and qGPoW2, were mapped via GWAS analysis. Through the integration of gene function annotation, transcriptome sequencing, and expression pattern analysis, we identified Glyma.06G255000 and Glyma.13G007000 as the key determinants of the pod length and width in vegetable soybeans, respectively. Furthermore, two kompetitive allele-specific polymerase chain reaction (KASP) markers, namely, S06-42138365 (A/T) and S13_628331 (A/T), were developed and effectively validated in 27 vegetable soybean accessions. Overall, our research identified genes that regulate the pod length and width and determined KASP markers for molecular marker-assisted selection breeding. These findings have crucial implications for the improvement of soybean crops and can contribute to the development of efficient breeding strategies. Full article