Search Results (1,889)

Data-driven models can be used to understand basin-wide hydrological processes and generate predictions for future conditions, particularly in cases of scarce data availability related to basin characteristics. Although they have long been applied in hydrological modeling, there is still limited information regarding their ability to produce reliable long-term projections under climate change conditions. This study evaluates the long-term predictive performance of data-driven models by employing a hybrid deep learning architecture combining Wavelet Transform (WT) and Deep Neural Network (DNN). The dataset used in this study was obtained from the Yamula Reservoir Basin, a semi-arid agricultural basin in Türkiye. Monthly streamflow was simulated based on climate projection data from the HadGEM2-ES model under the RCP4.5 and RCP8.5 scenarios. Results showed that the WT–DNN framework was successful in learning the system dynamics and reproducing observed streamflow behavior. The model produced continuous projections for the future period; however, these projections should be interpreted with caution due to the increasing uncertainty associated with long-term climate forcing and the sensitivity of data-driven approaches to shifts in climatic and hydrological regimes. Full article

Accurate and robust detection of leaf diseases is a key enabler for precision agriculture and large-scale crop health monitoring. Despite the strong generalization of modern one-stage detectors (e.g., YOLOv8), two domain-specific challenges remain: (i) weak or blurry lesion boundaries hinder precise localization, and (ii) low color contrast between diseased and healthy tissues forces models to rely on subtle texture patterns rather than salient shapes. To tackle these challenges, we reframe the core agricultural disease detection task as the identification of “asymmetric morphological anomalies” and propose a domain-tailored enhancement framework. First, we introduce an Edge Enhancement Module (EEM) that explicitly strengthens boundary-aware representations. Inspired by the natural symmetry of healthy leaves, our EEM is specifically designed to capture symmetry-breaking boundary discontinuities and localized asymmetric edges caused by disease lesions. Our method enhances edge and texture cues that are indicative of disease lesions, which often exhibit local asymmetries and boundary discontinuities. The EEM includes a Differential Normalized Pooling Block (DNPB) that highlights edge responses through discrepancies between max pooling and average pooling, which also models cross-group edge correlations. Second, the Lightweight Texture-Sensitive Feature Enhancement (LTSFE) mechanism amplifies texture-discriminative channels under low-contrast conditions by leveraging complementary global statistics and efficient channel mixing, all with negligible computational overhead. We evaluated our method on a self-constructed dataset of 106,434 images with 225,640 annotations covering diverse crops. Experiments show that the proposed method achieves state-of-the-art accuracy (81.54% mAP@0.5:0.95) while maintaining real-time inference (142 FPS), consistently outperforming strong baselines. Ablations confirm the effectiveness and complementarity of EEM and LTSFE, demonstrating that domain-specific architectural design, inspired by biological symmetry, can substantially improve agricultural vision systems. Full article

Stereo vision is essential for passive three-dimensional perception in resource-constrained applications that require low power consumption, predictable latency, and explainable geometry. Although deep learning architectures dominate recent benchmarks, the classical block-matching pipeline remains a foundational approach. Optimizing this pipeline involves navigating complex trade-offs among matching robustness, map density, and computational efficiency. This study systematically surveys and physically validates the classical stereo framework. After revisiting geometric first principles, three matching costs (SAD, NCC, ZNCC) are benchmarked alongside Sobel preprocessing and structural refinements, with subsequent validation using a calibrated consumer webcam rig. Middlebury benchmarks (2001–2021) indicate that while SAD fails under complex radiometric distortion, NCC consistently achieves superior quantitative metrics, incurring only a 1.2-fold computational overhead. Extending the disparity search range improves foreground localization, while block size imposes a trade-off between resolving the aperture problem and preserving fine geometric detail. To bridge theoretical analysis and practical deployment, the pipeline is validated using a custom-calibrated consumer stereo rig. The optimized Sobel-NCC architecture is then evaluated for real-time edge deployment on constrained hardware (NVIDIA Jetson Nano) and narrow-baseline sensors (OAK-D SR) in the context of agricultural robotic manipulation. By prioritizing metric precision over dense prediction, the classical pipeline reconstructs target surfaces with approximately 1 cm depth accuracy at 21 frames per second. These results demonstrate that optimized local algorithms offer deterministic and reliable geometric foundations for real-time edge-computed robotics. Although neural networks are essential for dense reconstructions in ill-posed regions, the foundational principles established here remain indispensable for advanced stereo vision system deployment. Full article

Accurate and scalable urban land cover mapping is critical for sustainable urban planning and environmental management. While deep learning models offer powerful tools for this task, their performance is often constrained by the need for vast, manually labeled datasets, which are costly and challenging to acquire for diverse urban environments. To address this limitation, we propose the Cross-Scale U-Net, an original, highly adaptable operational framework that systematically exploits the inherent scale effects of remote-sensing imagery to optimize transfer learning. By operationalizing prior theoretical findings on receptive fields, this workflow provides an actionable method for users to manipulate spatial resolution, identify an optimal scale to bridge the domain gap, and subsequently automate feature extraction with significantly reduced manual effort. Using the well-annotated ISPRS Potsdam dataset as the source domain, our framework transfers learned knowledge to classify National Agriculture Imagery Program (NAIP) data from Phoenix, AZ (2015), into four primary land cover classes. We systematically evaluated the framework’s performance across spatial resolutions ranging from 15 cm to 100 cm, achieving a peak overall accuracy (OA) of 82.45%. To assess generalizability, the model was applied in a label-free transfer scenario to NAIP imagery from Las Vegas, NV (2015), and Phoenix, AZ (2013 and 2019), consistently delivering OA values above 70%. In a comparative analysis, the Cross-Scale U-Net significantly outperformed traditional classification techniques. While our current empirical validation is focused on arid urban environments due to experimental constraints, the framework introduces a highly flexible, actionable scale-adjustment process. This approach offers a scalable workflow that can be tailored to various landscape scales—such as expanding to coarser resolutions for large-scale forests or protected areas—delivering high-fidelity maps while mitigating data scarcity. Full article

With the occurrence of global climate change and the depletion of agricultural water resources, there is a growing need to develop rapid, non-destructive, and autonomous plant health monitoring systems. As an economically valuable crop, Ocimum basilicum L. (basil) is sensitive to changes in water availability and may exhibit stress-related morphological variations under drought and over-irrigation conditions. However, due to the visual similarity of leaf symptoms under drought stress, waterlogging stress, and optimal irrigation conditions, accurately distinguishing these conditions remains challenging in practical applications. To address this challenge, this paper presents an attention-based dual-branch deep learning framework designed to extract both subtle leaf details and channel-related features from high-resolution plant images. By combining the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) mechanism in a parallel structure, the proposed network improves the analysis of high-resolution images with an input size of 720 × 720 pixels. Under controlled environmental conditions, with ground-truth labels obtained using soil moisture sensor measurements, the proposed model was compared with eight deep learning architectures, including DenseNet121, InceptionV3, and VGG16. The proposed model achieved a hold-out evaluation accuracy of 99.54%, outperforming the second-best model, DenseNet121, which achieved 96.43%. In addition, the proposed model reached a class-specific precision value of 100% for the Drought Stress category and achieved an area under the receiver operating characteristic curve of 1.00 under the controlled experimental setting. Taylor Diagram analysis also indicated that the model closely preserved the variability pattern of the reference data. These results suggest that the proposed application-specific framework may support non-destructive basil water-stress detection under controlled conditions. After further validation with larger datasets, different cultivars, variable environmental conditions, and real-world agricultural scenarios, the proposed approach may contribute to precision irrigation management and sustainable agricultural production. The contribution of this study should be interpreted as an application-specific implementation and evaluation of complementary attention mechanisms for controlled-environment basil water-stress classification, rather than as the introduction of a fundamentally new deep learning methodology. Full article

Precision agriculture increasingly relies on machine learning applied to high-resolution data acquired by unmanned aerial vehicles (UAVs) to support crop monitoring, stress detection, and yield forecasting. This survey presents a structured review of machine learning methods for UAV-enabled precision agriculture and organizes over 100 peer-reviewed studies within a unified four-dimensional taxonomy defined by sensing modality, data type, model family, and analytical task. The taxonomy enables systematic comparison across RGB, multispectral, hyperspectral, LiDAR, and IoT data sources and across classical machine learning, deep learning, hybrid sequential models, and emerging transformer-based architectures. We analyze how modeling choices interact with data characteristics to influence robustness, cross-environment generalization, computational efficiency, and deployment feasibility on UAV and edge platforms. Recurring challenges include limited labeled data, domain shift across seasons and fields, multimodal heterogeneity, occlusion, and real-time processing constraints. We identify emerging research directions, including data-efficient learning, representation-level multimodal fusion, domain adaptation, lightweight architectures for embedded deployment, and uncertainty aware decision support. By formalizing the landscape through a unified taxonomy, this survey provides a foundation for designing scalable, robust, and deployable machine learning systems for next-generation precision agriculture. Full article

Context: Accurate citrus crop mapping is essential for agricultural monitoring, production planning, and supply-chain management, particularly in Brazil, one of the world’s leading orange producers and the leading orange-juice exporter. Satellite image time series from Sentinel-2 provide rich spectral and temporal information for crop identification. However, citrus mapping remains challenging due to fragmented agricultural landscapes, cloud contamination, class imbalance, and spectral overlap with other vegetation classes. Problem: Conventional machine learning models often depend on handcrafted vegetation indices, while attention-based deep learning models may require larger datasets and can become unstable under geographically constrained conditions. Therefore, there is a need for a compact and robust deep learning architecture capable of extracting citrus phenological signatures directly from multispectral time-series data. Methods: This study evaluates a Spatio-Temporal Pixel-Set Encoder Convolutional Neural Network (PSE-CNN) for citrus crop classification in the immediate geographic regions of São João da Boa Vista and Mogi Guaçu, São Paulo, Brazil. MapBiomas Collection 10.1 data from 2019 to 2024 were used to derive reference polygons, and Sentinel-2 imagery was processed into cloud-masked, 15-day temporal composites using ten spectral bands. The proposed PSE-CNN was benchmarked against PSE-TAE, PSE-Transformer, Random Forest, and XGBoost using spatially grouped data partitioning and temporal test years. Results: The proposed PSE-CNN achieved the highest Unified F1-Score of $0.704$ and the lowest coefficient of variation of $3.03\%$, indicating stronger inter-annual stability across test years and random seeds among the evaluated models. It also outperformed classical models that relied on handcrafted vegetation indices and demonstrated greater overall stability than attention-based deep learning alternatives. Conclusions: The results indicate that combining pixel-set encoding with temporal convolution provides a resource-aware and stable framework for retrospective citrus crop mapping from Sentinel-2 satellite image time series. These findings suggest that PSE-CNN can support scalable agricultural monitoring, contributing to sustainable crop inventory systems in regions where labeled data and computational infrastructure are limited. Full article

Monitoring urban biodiversity is essential for designing resilient and sustainable cities. Urban trees provide a wide range of ecosystem services (ESs), including air pollution reduction, urban heat island mitigation, and psychological benefits for citizens. Accurate and updated tree inventories are therefore essential tools for urban environmental monitoring. However, existing urban tree inventories are often incomplete or outdated, especially in private areas, limiting accurate ES assessment and urban planning. Earth observation satellite missions, particularly very-high-resolution multispectral (VHR-MS) imagery, offer a valuable alternative to field surveys for gathering information on urban environments. This work proposes a deep learning (DL) framework based on VHR-MS satellite imagery for the automatic generation of accurate urban tree inventories. DL models reduce human effort and save operational time by automatically learning complex representations and patterns from satellite imagery. The proposed encoder–decoder architecture extends prior point-based detection approaches by integrating a ResNet-50 backbone and a percentile-based threshold calibration procedure. Given the lack of suitable training data covering heterogeneous and densely vegetated urban environments, a dedicated dataset was constructed from VHR-MS satellite imagery acquired over the Lombardy region (Italy). The dataset encompasses a wide range of land uses and land covers, including residential and industrial zones, public parks, private gardens, and agricultural areas. Through the photointerpretation of more than 2800 images, precise coordinates for more than 50,000 manually annotated trees were obtained. The DL model is trained with point-level annotations, enabling precise localization of individual trees while reducing annotation ambiguity in dense urban contexts. On the Lombardy dataset at 30 cm/px resolution, the proposed framework achieves 86.72% Precision, 66.92% Recall, an F1-score of 75.54%, and a localization error of 1.473 m. Full article

Saudi Arabia is expanding its domestic coffee sector under Vision 2030, yet coffee farming remains vulnerable to leaf diseases and pest damage. Image-based artificial intelligence studies conducted under Saudi field conditions remain limited, particularly in relation to assessing image-based visible disease severity. This study designs a hierarchical deep learning framework for screening coffee leaf diseases using field-collected images of Saudi coffee leaves. Three tasks were addressed: binary health status classification, four-class disease or pest damage identification, and binary visible severity classification. A dataset of 550 RGB images was collected from Al-Dayer Governorate, Jazan, under natural field conditions. ResNet50, DenseNet121, and EfficientNet-B0 were evaluated via transfer learning in two phases: a Saudi-only phase and an integrated phase that combined Saudi data with selected JMuBEN and JMuBEN2 samples. In the Saudi-only phase, ResNet50 achieved 96.47% accuracy for binary classification, while DenseNet121 achieved 68.66% and 78.12% for disease and visible severity classification, respectively. In the integrated phase, performance improved to 99.74%, 97.76%, and 97.37%. These integrated-phase results are interpreted as evidence that dataset expansion and increased visual diversity can improve model performance, rather than as definitive estimates of field deployment performance. The results show that binary classification is feasible under limited local data, whereas fine-grained disease classification is more constrained by dataset size and class imbalance. Grad-CAM visualizations were used to support qualitative interpretability and should not be interpreted as biological validation of disease localization. The framework is positioned as a decision-support screening approach that requires further expert-validated, multi-farm, and multi-season evaluation before deployment. Full article

The early and accurate recognition of fruit tree pests and diseases is essential for safeguarding fruit yield, quality, and sustainable agricultural production. Conventional manual inspection methods are inadequate for meeting the demands of continuous, objective, and real-time monitoring in large-scale orchards. Following the framework of “model evolution–key challenges–edge-intelligent deployment,” this review systematically summarizes advances in deep learning-based recognition of fruit tree pests and diseases, and compares the effectiveness and limitations of representative methods from the perspectives of data complexity, model generalization and robustness, real-time inference, cross-modal fusion, and trustworthy diagnosis. Existing studies indicate that CNNs, attention mechanisms, Transformers, multimodal fusion, and lightweight networks have promoted the transition of fruit tree pest and disease recognition from image classification to object detection, lesion segmentation, and edge deployment; however, sample scarcity, class imbalance, insufficient cross-domain generalization, black-box decision-making, energy constraints, and long-term robustness remain major bottlenecks for field application. Future research should focus on open orchard environments and develop data-efficient, interpretable, low-power, and continuously updatable edge-intelligent recognition systems, thereby advancing precision agriculture and smart orchards. Full article

With the growing global population, intensifying resource constraints, and deepening climate change impacts, agriculture faces dual challenges of ensuring food security and advancing sustainable development. Artificial intelligence (AI) has emerged as a transformative technology, penetrating the entire crop production chain and offering innovative solutions to traditional agricultural bottlenecks. This paper systematically reviews AI applications in five core domains: biotic stress monitoring, soil health management, precision operation, supply chain optimization, and climate-resilient agriculture. It further categorizes and analyzes four key technical pathways—deep learning, sensor fusion, data-driven methods, and hybrid modeling—while critically examining major challenges across data, technology, implementation, and ethics/policy dimensions. Future directions are discussed from technological innovation, scenario expansion, implementation guarantees, and sustainability orientation. Research findings show that AI has achieved technical validation in pest/disease detection, soil parameter modeling, and intelligent spraying, with accuracy exceeding 85% in some cases. However, regional data bias, insufficient model generalization, and the digital divide still hinder large-scale deployment. Moving forward, coordinated efforts in technological innovation and policy support are required to promote inclusive, standardized, and sustainable AI applications in crop production. Full article

The Liuwan burial complex is the largest known prehistoric clan-based cemetery in the upper Yellow River region, making its preservation vital for Chinese cultural heritage and sustainable local development. To address threats from unregulated agricultural activities and illegal looting, this study proposes a non-invasive preventive protection approach. Surface-visible tombs were identified using low-altitude UAV imagery and deep learning models (YOLOv8n, YOLOv5n, RT-DETR-l, and Hyper-YOLO). By incorporating environmental factors such as elevation, slope, aspect, distance to water, Topographic Wetness Index, and Topographic Position Index, potential tomb distributions were modeled on the Biomod2 platform and key environmental drivers were analyzed. Hyper-YOLO achieved the highest identification accuracy (94.4%). The optimal model, EMwmean (TSS = 0.492, AUC = 0.798), showed that high-potential tomb areas are mainly concentrated in the central region, with tombs preferring elevations of 1964–1978 m, south-facing slopes, and slopes of 13.14–19.19°. This study demonstrates the feasibility of using deep learning to identify surface-visible tombs and predict their potential distributions based on environmental characteristics, thereby providing priority references for heritage protection in Liuwan rather than a definitive inventory of all subsurface remains or cultural phases. Full article

Weed detection is an important part of precision agriculture because it allows farmers to manage weeds more efficiently and reduce unnecessary herbicide use. With the use of UAVs, it is now possible to capture high-resolution images of agricultural fields, but identifying weeds from these images is still challenging due to complex backgrounds, lighting variations, and the visual similarity between crops and weeds. In this study, an improved YOLOv7-based approach is developed to address these challenges using UAV imagery collected from rainfed cotton fields in the Texas Panhandle. The original dataset consisted of high-resolution UAV images, which were divided into smaller patches and manually annotated to label weed and cotton classes. After cleaning the dataset and applying simple augmentation techniques, a total of 8396 images were used for training and testing. To improve detection performance, two modifications were introduced: Convolutional Block Attention Module (CBAM) to help the model focus on important features and Bidirectional Feature Pyramid Network (BiFPN) to improve how information is shared across different scales. Three models—YOLOv7-CBAM, YOLOv7-BiFPN, and the combined CB-YOLOv7—were evaluated. The results show that CBAM helps detect more weed instances, BiFPN reduces false detections, and the combined model gives the best overall performance, achieving an mAP@0.5 of 0.89 and an F1-score of 0.84. Overall, the study shows that improving both the dataset and the model can lead to more reliable weed detection under real field conditions. The proposed approach can be useful for identifying weeds in cotton fields using UAV imagery and can support better crop management and more efficient use of herbicides in precision agriculture. Full article

Drought is a slowly evolving, multi-driver hydro-meteorological hazard whose accurate early prediction is a cornerstone of climate-smart agriculture and water-resource planning. Existing data-driven drought forecasting frameworks suffer from three persistent limitations: (i) most models concatenate heterogeneous climate variables into a single flat feature vector, implicitly assuming a single dominant driver such as precipitation, even though atmospheric moisture demand, radiation and wind-mediated evapotranspiration co-determine drought onset; (ii) wavelet preprocessing is typically applied to the full series, introducing future-information leakage that violates the operational causality requirement of forecasting; and (iii) most architectures predict a single horizon and provide no causal attribution explaining when, where and which climatic variables initiated the event. This study proposes WaveDroughtNet, a multi-modal, multi-horizon deep-learning framework that addresses these limitations through five integrated components: (a) a strictly causal Daubechies-4 wavelet decomposition computed in a rolling fashion; (b) six modality-specific encoders with stochastic modality dropout (p = 0.15); (c) cross-modal multi-head attention with four heads; (d) a four-layer temporal convolutional network (TCN) backbone with dilation factors yielding a 240-step receptive field; and (e) a post hoc DroughtOriginTracer that combines temporal attention, modal-attribution and inter-district propagation scans. The Standardised Precipitation Evapotranspiration Index (SPEI), used as the supervisory target, is computed following the canonical Vicente-Serrano formulation. water balance $D=P-\mathrm{P}\mathrm{E}\mathrm{T}$ (Hargreaves PET) at a 4-week (≈1-month) timescale, fitted with a three-parameter log-logistic distribution via L-moments, validated by Kolmogorov–Smirnov goodness-of-fit testing ($\alpha =0.05$) per district, and standardised through the inverse-normal cumulative distribution function. Trained on 18,304 weekly district records from NASA POWER reanalysis (2014–2025) covering all 32 districts of Tamil Nadu, India, WaveDroughtNet uses only 256,869 parameters and produces, in a single forward pass, four forecasts (1 week, 1 month, 3 months, 1 year). On the held-out 2024 test partition ($N=1728$), the model attains weighted $F1=0.9221$ and $R^2=0.8512$ at the 1-week horizon, and weighted $F1=0.8498$ and $R^2=0.6812$ at the 1-year horizon. Diebold–Mariano tests confirm that WaveDroughtNet significantly outperforms naive persistence, seasonal naive, LSTM, ConvLSTM and a vanilla Transformer at the 3-month and 1-year horizons (p < 0.001). The DroughtOriginTracer successfully back-projects 15 Coimbatore events to causal origins 29–41 weeks prior to onset. We explicitly acknowledge three limitations that constrain operational deployment in its current form—zero severe events in the 2024 test partition ($F{1}_{severe}$ = 0.000), static inter-district modelling, and absence of vegetation-index supervision—and propose concrete mitigation pathways in the Discussion. Full article

Plant recognition plays a vital role in agriculture and biodiversity monitoring, and deep learning, particularly convolutional neural networks (CNNs), has gained increased attention for automating this task. However, CNNs have a limitation in their ability to handle complex patterns due to the difficulty in capturing global contextual information. Furthermore, plant datasets are often created in laboratory environments that minimize discrimination challenges, enabling the analysis of model performance. This study proposes a hybrid deep learning model, HDL-PlantNet, for real-world plant recognition on the primary dataset, the Cyprus Seasonal Flora Image Dataset (CSFID), comprising 27 plant species. The HDL-PlantNet model integrates an EfficientNetV2-S convolutional backbone with a Transformer encoder to capture both spatial contextual and long-range dependencies. Additionally, the Swedish Leaf Dataset is used as a supplementary dataset to analyze the consistency of the HDL-PlantNet under controlled environments. Five benchmark CNN models are used for comparative evaluation, and statistical tests and an ablation study are conducted to assess the results. The proposed model achieved the highest observed Macro-F1 and Macro-AUC scores among the evaluated models, reaching 90.06% and 99.59%, respectively. The results demonstrate that combining convolutional and Transformer architectures yields computationally effective performance in fine-grained plant classification while maintaining a compact model size suitable for further research. This study contributes to real-time plant identification studies and supports informed ecological decision-making. Full article