Search Results (632)

Efficient nitrogen (N) management is essential for sustaining crop productivity while minimizing environmental impacts associated with nitrogen losses. However, the high spatial and temporal variability of soil nitrogen dynamics and crop nitrogen status makes field-scale monitoring challenging, while conventional soil and plant sampling methods are labor-intensive, destructive, and provide limited spatial coverage. Recent advances in remote sensing technologies and machine learning (ML) offer promising alternatives for high-throughput, non-destructive monitoring of crop nitrogen status and related nitrogen dynamics in agroecosystems. This review synthesizes current progress in the use of proximal and remote sensing platforms, including unmanned aerial vehicles (UAVs), satellites, and ground-based sensors for assessing crop nitrogen status and inferring soil nitrogen availability. We examine spectral, thermal, and structural indicators, together with emerging sensor-fusion and time-series approaches. We also evaluate ML algorithms, including emerging foundation model approaches, for estimating crop nitrogen status and inferring soil nitrogen indicators, highlighting their performance, limitations, and transferability across environments. Particular emphasis is placed on field-scale applications in heterogeneous and water-limited systems, where nitrogen-water interactions critically influence crop responses. Finally, we discuss current challenges, including data scarcity, model generalization, and operational constraints, and outline future directions toward integrated, real-time decision support systems for precision nitrogen management. Overall, this review provides a comprehensive framework for leveraging remote sensing and data-driven approaches to improve nitrogen monitoring and enhance nitrogen use efficiency in diverse cropping systems. Full article

Administrative document analysis represents a critical organizational challenge: organizations generate vast quantities of documents containing valuable strategic insights, yet traditional analysis approaches remain manual, opaque, and fragmented across systems, leaving organizations vulnerable to missed opportunities and delayed decision making. Conventional document management systems relying on keyword search and isolated machine-learning pipelines lack intelligent reasoning capabilities and autonomous coordination, leaving critical insights buried in unstructured documents. Organizations relying on traditional document processing tools and lacking explainable AI remain blindsided by complex patterns and correlations that could be anticipated and leveraged for strategic advantage. We introduce IKEA, an intelligent document analysis framework that integrates Reasonable AI (explainable reasoning agents) with Agentic AI (autonomous intelligent agents) to provide transparent, autonomous knowledge extraction from administrative documents. Our system employs GPT-3.5-turbo powered reasoning agents that autonomously extract knowledge, generate transparent reasoning chains, and provide conversational AI assistance, all while maintaining end-to-end explainability through step-by-step reasoning decomposition, confidence breakdown analysis, evidence extraction, and assumption identification. Evaluated on a primary corpus of 50 administrative documents (performance reports, incident reports, meeting minutes, policy documents) with 200+ performance metrics and 100+ AI-generated insights, the Reasonable AI agents achieve 87% explanation accuracy aligned with expert assessments, while the Agentic AI agents demonstrate 92% knowledge extraction accuracy with 85% reasoning quality score. Against state-of-the-art baselines under matched conditions—including GraphRAG, DocAgent (text-adapted), dense RAG, and ReAct—IKEA attains the highest entity $F_1$ and a large margin on explanation accuracy and auditability. Cross-dataset tests on Kleister (Charity and NDA), a DocVQA text-only subset, and an external 25-document administrative corpus confirm that these gains transfer beyond the primary corpus, with only a modest drop relative to in-domain performance. On the primary corpus, the integrated framework also delivers a 40% reduction in document analysis time and a 35% improvement in insight discovery rate compared with traditional manual analysis. Full article

Background/Objectives: Chronic kidney disease is a growing global health concern, necessitating effective tools for early detection and monitoring. While non-contrast T1-weighted magnetic resonance imaging offers a non-invasive means to assess kidney morphology, robust automated segmentation remains challenging due to limited annotated data, high inter-patient variability, and low signal-to-noise ratios. Methods: In this study, we address these obstacles by developing and evaluating a series of frugal learning methodologies for kidney segmentation in non-contrast MRI. Building upon the U-Net architecture, we aim to maximize segmentation accuracy despite scarce labeled data. Our experimental framework leverages three diverse datasets to evaluate performance-boosting strategies such as transfer learning: a clinically relevant local cohort (the Barlicki dataset) as the primary target domain and two auxiliary public datasets (AMOS22 and AbdomenCT). Utilizing these data streams, we systematically compare seven frugal learning strategies incorporating data augmentation, semi-supervised learning, and weak supervision against a fully supervised baseline. Results: The results demonstrate that frugal learning methods enable accurate and reliable kidney segmentation while substantially reducing the need for manual annotations. The best-performing semi-supervised and transfer learning approaches achieved a Dice similarity coefficient of 0.89, which was only moderately lower than that of the fully supervised model (Dice = 0.92). Conclusions: This work highlights the potential of data-efficient deep learning techniques to accelerate the adoption of automated kidney segmentation in clinical workflows, particularly in settings where annotated medical images are limited. Full article

To address the challenges of low detection accuracy and weak generalization in identifying mining-induced ground fissures from UAV imagery, caused by their slender and discontinuous morphology, complex background clutter, and multi-scale surface features, this paper proposes an enhanced deep semantic segmentation model, SAG-DeepLabV3+ (with Spatial Vision Transformer, Attention mechanisms, and Adaptive Gated Fusion). Specifically, to enhance global context modeling and fine boundary delineation, we introduce a Spatial Vision Transformer (SVT) branch within the Atrous Spatial Pyramid Pooling (ASPP) module. We further employ a dual attention mechanism, sequentially combining Squeeze-and-Excitation (SE) and a Convolutional Block Attention Module (CBAM), for progressive channel and spatial feature refinement. Moreover, an Adaptive Gated Fusion (AGF) module is designed to dynamically optimize the fusion of multi-level decoder features. Experiments on a dedicated UAV-based mining fissure dataset comprising 1280 annotated images show that SAG-DeepLabV3+ achieves a state-of-the-art mean Intersection over Union (mIoU) of 79.52% (with Xception backbone) and 79.19% (with lightweight MobileNetV2 backbone), surpassing DeepLabV3+, U-Net, and PSPNet by a significant margin. Furthermore, by leveraging transfer learning (pre-training on the public CrackVision12K dataset and fine-tuning on our mining fissure dataset), the model’s mIoU is further elevated to 82.04%, demonstrating superior generalization capability. The proposed SAG-DeepLabV3+ effectively balances high accuracy with operational efficiency, fulfilling the potential demand for lightweight automated fissure monitoring under resource-limited field deployments, and lays a foundation for subsequent real-time on-site deployment verification. Full article

Human interaction with the environment depends on the integration of sensory input, cognitive processing, and motor output within dynamic sensorimotor loops. These processes are supported by distributed neural circuits and shaped by learning, memory, and neuroplasticity across the lifespan. This review synthesizes current understanding of the mechanisms underlying sensorimotor integration and highlights how experience-dependent plasticity supports functional recovery and performance optimization in both health and disease. Disruptions such as traumatic brain injury, neurodegenerative disease, and aging may frequently result in combined cognitive and motor impairments. Here, we review non-invasive interventions that leverage neuroplasticity, including physical activity, motor training, and cognitive training, with increasing emphasis on integrated cognitive–motor approaches. Emerging technologies such as virtual reality provide ecologically valid, immersive environments that simultaneously engage perception, cognition, and action, with the potential to enhance training outcomes. However, variability in effectiveness and limited evidence for far transfer remain key challenges. To address these limitations, we highlight the integration of immersive training with objective biological measures. In particular, proton nuclear magnetic resonance (¹H NMR)-based metabolomics offers a promising, non-invasive approach to identify biomarkers of neuroplastic adaptation. The integration of robust biomarker tools may facilitate the development and assessment of effective precision cognitive–motor interventions to optimize rehabilitation approaches and help build resilience in vulnerable individuals. Full article

Exhaled breath analysis has emerged as a promising non-invasive approach for disease diagnosis, leveraging gas sensors for their high sensitivity, portability, and real-time monitoring capabilities. Two-dimensional nanomaterials, such as graphene, transition metal dichalcogenides (TMDs), MXenes, black phosphorus, and metal–organic frameworks (MOFs), exhibit exceptional gas-sensing properties due to their atomic-scale thickness, ultra-large specific surface area, and tunable electronic structures. These characteristics enable enhanced gas adsorption and room-temperature operation, making them ideal for detecting ppb-level biomarkers like acetone, ammonia, and nitric oxide in breath. However, sensors based on pristine 2D materials face challenges including slow response/recovery kinetics, poor stability, weak humidity resistance, and limited selectivity in complex breath environments. To address these limitations, functionalization strategies have been developed to engineer material properties. Key approaches include heteroatom doping to modulate electronic band structures, heterojunction construction to facilitate charge transfer and improve selectivity, and noble metal decoration for catalytic enhancement of gas adsorption. Additionally, light irradiation has been employed to regulate the carrier concentration on the surface of sensitive materials. These strategies significantly boost sensor performance, achieving ppb-level detection limits, robust humidity resistance, and rapid response. Future directions involve integrating functionalized 2D materials into wearable, multiplexed sensor arrays for simultaneous biomarker detection, coupled with machine learning for real-time diagnostic platforms. Full article

Few-shot domain adaptation (FSDA) has become an important approach for cross-domain intrusion detection by enabling models to leverage limited labeled target data under distribution shifts. Although numerous adaptation methods have been proposed, their effectiveness often varies considerably across transfer scenarios, leading to inconsistent performance across domains. This study investigates how prototype-based transferability can be used to characterize source–target compatibility prior to adaptation. To this end, a transferability-aware perspective on FSDA is presented by distinguishing between intra-domain separability, which characterizes the internal class structure of a domain, and cross-domain transferability, which reflects how effectively source-derived representations generalize to a target domain. Based on this distinction, a set of asymmetric transferability metrics is introduced to characterize prototype-based transferability from complementary perspectives. Across the evaluated transfer scenarios, stronger intra-domain separability did not necessarily coincide with better cross-domain transferability. Furthermore, the empirical results indicate that different adaptation strategies exhibit different behaviors across the examined transfer directions. Across the two evaluated transfer directions, the prototype-based transferability analysis and the few-shot adaptation results exhibit different behaviors. While target-only few-shot learning performs competitively in one transfer direction, prototype-based alignment methods provide larger improvements in the other, illustrating that adaptation performance reflects not only source–target compatibility but also intrinsic target-domain separability and the adaptation process itself. These observations provide an empirical perspective for interpreting the varying performance of existing FSDA methods and highlight the importance of considering transfer conditions when selecting adaptation strategies for cross-domain intrusion detection. Full article

Ultrashort Pulse Laser (USPL) ablation is a versatile manufacturing process, but predicting its outcomes across different materials often requires extensive and costly experimentation. This work provides a machine learning framework that leverages transfer learning to bridge the gap between simulation and experimental data, enabling accurate prediction of material behavior during USPL ablation under data-scarce conditions. We generated a high-fidelity computational dataset using the LS-PLUME^® simulator for Stainless Steel 316 (SS 316), and then complemented with targeted experimental studies on SS 316, Silicon (Si) and Aluminum (Al) to capture real-world deviations. A model pre-trained on the simulation data was successfully adapted to the experimental domain, effectively absorbing systematic deviations and extending its predictive capability to new materials with minimal experimental data. Our transfer learning framework bridged the simulation-to-experiment gap using minimal data, successfully fine-tuning a base model trained on 3075 samples with just 49 experimental points for Si and 46 for Al with mean percentage errors under 5%, thus demonstrating high data efficiency for industrial laser surface texturing. Furthermore, the application of explainable artificial intelligence revealed that the model predictions are more sensitive to peak fluence and the number of passes, with SS 316 exhibiting higher overall sensitivity to input parameter variations than Si and Al, thus providing actionable physical and process-level insight relevant for industrial optimization. Full article

Satellite Synthetic Aperture Radar (SAR) is an established technology for studying and monitoring archaeological landscapes, providing insights into surface morphology and the presence of near subsurface features. However, its application in large-scale archaeological prospection is limited by the lack of robust, automated methods for SAR data analysis. This study introduces a novel Deep Learning pipeline to automatically detect and segment archaeological settlement mounds, known as tells, in central Iraq on satellite SAR data. The pipeline leverages a state-of-the-art supervised method for instance segmentation, YOLOv8-Seg, and medium-resolution satellite SAR products, specifically the Copernicus Sentinel-1 Interferometric Wide Swath Mode Ground Range Detected and Copernicus Global 30-m Digital Elevation Model products. The model identifies tell sites with an Average Precision of $0.495\pm 0.010$ and a pixel-wise Intersection over Union of $0.361\pm 0.048$ over the test areas. Archaeological interpretation of the model’s inferences confirms its reliability in locating and segmenting archaeological sites, leading also to the identification of previously unmapped potential sites. After a main test in central Iraq, the proposed workflow demonstrates promising transferability to a nearby test area in Iran, although with a need for regional fine-tuning to account for inherent variations in feature morphology and environmental context. This research establishes a baseline for future Deep Learning applications in Synthetic Aperture Radar-based archaeological prospection. Full article

South Africa faces significant challenges in monitoring air pollution from different provinces due to the sparse nature of the sensor network and heterogeneous pollutant sources. Notably, some provinces continue to record a limited amount of data on air pollution, thus making monitoring in those locations problematic. Fortunately, the capabilities of deep learning models to facilitate effective monitoring in data-scarce locations have been highlighted by researchers; however, these models within the context of transfer learning still lack transparency and uncertainty quantification. Using air pollutants and meteorological factors, this study proposes a transfer learning model for particulate matter (PM_2.5) prediction in a data-scarce region. This transfer learning (TL) model leverages an adaptive Bi-directional Gated Recurrent Unit (adaBiGRU) with explainable artificial intelligence (xAI) and uncertainty quantification (UQ) to provide a novel uncertainty-aware adaptation transfer learning (UATL_adaBiGRU) model for a data-scarce location. Variant models based on the adaBiGRU technique, such as the temporal convolution network adaBiGRU (TCN-adaBiGRU) and domain-adversarial neural network adaBiGRU (DANNadaBiGRU), are presented as comparative models. The performance evaluation metrics are root mean squared, R² score and mean squared error. The R² score of pre-trained models in source domain is adaBiGRU (0.888), DANN_adaBiGRU (0.7788) and TCN_adaBiGRU (0.876). Furthermore, other comparative TL models include GRU (0.898), MLP (0.802) and adaptive LSTM (0.886). Afterwards, the pre-trained baseline model (adaBiGRU) was fine-tuned in the target domain dataset and the unpromising result contributed to the proposition of the UATL_adaBiGRU model for a data-scarce location, with R² score of 0.9618. Uncertainty assessment metrics results were also presented for the proposed model. Ablation assessment demonstrates that each component of the UATL_adaBiGRU contributes to enhancing the predictive performance. Again, the Diebold–Mariano (DM) test statistic demonstrates a statistically significant difference between baseline model and UATL_adaBiGRU model. Finally, the local interpretable model-agnostic explanation highlights multi-scaled features as contributing towards the prediction of PM_2.5 in the target domain. In view of this result, model fine-tuning is strongly recommended to enhance the robustness of the proposed uncertainty-aware adaption model in data-limited regions in South Africa. Full article

Background: Malaria is a life-threatening disease caused by Plasmodium species, which is endemic in tropical and subtropical regions worldwide. In clinical settings, experienced parasitologists perform microscopic examinations of thick/thin blood slides. This method is labour-intensive and is adversely affected by inter- and intra-observer variability among the microscopists. The present study aimed to develop a malaria screening algorithm using computer vision to identify and classify malaria parasite-infected red blood cells (RBC) from microscopic blood slide images. Methods: The proposed classification methodology first employs digital image processing techniques, the watershed transform, to preprocess the raw images, followed by connected component labelling to accurately segment and isolate individual RBCs from the background. To classify these segmented cells as either normal or infected, convolutional neural networks (CNNs) were utilized, leveraging their ability to automatically extract relevant features through deep, hidden layers, thus eliminating the need for manual feature engineering. Results: To compare and determine the most effective classification engine, the study developed and evaluated five distinct models: four well-established transfer learning architectures (VGG16, VGG19, DenseNet121, and InceptionV3), alongside a newly proposed custom CNN model. A total of 2422 segmented RBC images were used for the training, and 692 different images were used for testing, with the VGG model showing the best accuracy at 99.57%. The proposed CNN architecture also showed competitive results with 99.14% accuracy. Conclusions: Transfer learning models demonstrated remarkable accuracy for malaria parasite classification from blood smear slides, with VGG19 (99.57%) achieving the highest accuracy on diverged datasets for the test images. The analysis demonstrates the potential of this approach as a computational aid for future image-based malaria screening in conjunction with existing diagnostic tests. Full article

Respiratory diseases are a major global health challenge. However, identification of respiratory diseases is often limited by subjectivity, environmental noise and inter-clinician variability. This study presents an explainable multimodal deep learning framework for recording-level multiclass classification of respiratory audio signals. The proposed system integrates two complementary representations—a spectro-temporal encoder based on a CNN–BiLSTM-attention architecture and a handcrafted acoustic-feature encoder capturing acoustic descriptors commonly used in respiratory-audio analysis, including MFCCs, zero-crossing rate, spectral centroid, spectral bandwidth, chroma, RMS energy, and spectral rolloff features. These branches are combined through late-stage fusion to leverage both data-driven representation learning and domain-informed acoustic cues. The proposed model was trained and internally evaluated on the Asthma Detection Dataset Version 2, comprising five respiratory categories: bronchial disease, asthma, COPD, healthy, and pneumonia. Mono conversion, resampling to 16 kHz, 100–2000 Hz band-pass filtering, amplitude normalisation, fixed 4 s trimming or zero-padding, training-only augmentation, handcrafted-feature extraction, mel-spectrogram generation, quality control auditing, and stratified recording-level partitioning have been applied in the pre-processing steps. Across five repeated experiments with different random seeds, the proposed hybrid model achieved a mean held-out recording-level test accuracy of $0.9099\pm 0.0163$, balanced accuracy of $0.8936\pm 0.0152$, macro F1-score of $0.8937\pm 0.0177$, macro ROC–AUC of $0.9867\pm 0.0010$, and macro PR–AUC of $0.9489\pm 0.0044$. Conventional machine learning baseline comparisons showed that the proposed model achieved stronger internal accuracy, balanced accuracy, macro recall, macro F1-score, and macro ROC–AUC than classical machine learning algorithms trained on handcrafted acoustic features, although Random Forest remained competitive in macro PR–AUC. Ablation analysis shows that the deep spectro-temporal branch was the primary contributor to predictive performance, while the handcrafted branch provided complementary interpretable acoustic information rather than consistently improving all classification metrics. Explainability was incorporated using Grad-CAM and Integrated Gradients for spectrogram-based interpretation and SHAP for handcrafted-feature attribution. Domain-shift evaluation on the ICBHI Respiratory Sound Database and a COPD-focused cohort revealed substantial dataset shift effects, including poor healthy-case recognition on ICBHI and seed-dependent COPD recognition in the COPD-focused cohort. Identifier-aware sensitivity analyses showed lower performance than the main recording-level split, suggesting that subject-like or source-level overlap may inflate internal performance estimates. The findings should be interpreted as promising internal held-out recording-level algorithmic performance with limited external transfer, rather than evidence of readiness for clinical use. Full article

Floating liquefied natural gas (FLNG) facilities integrate natural gas liquefaction, storage, and offloading into a single vessel. During ship-to-ship (STS) side-by-side offloading, an LNG carrier (LNGC) moors alongside the FLNG to transfer liquefied cargo through a loading-arm system. The hydrodynamic interactions between the two vessels, combined with environmental loads, can lead to excessive relative motions that pose a risk of collision or damage to the loading arms and fenders. Accurate short-term prediction of vessel motions would provide operators with advance warning of potentially dangerous conditions, allowing preventive actions to be taken. This study presents a data-driven approach to short-term motion prediction using experimental data obtained from comprehensive basin model tests of an FLNG system. The model tests covered 15 environmental conditions, including survival conditions (100-year return period) and operating conditions (1-year return period), under both single-vessel and side-by-side configurations. Three prediction methods were evaluated: an autoregressive linear model, a single-degree-of-freedom multi-layer perceptron, and a multi-head attention cross-coupling network (MAC-Net) that leverages temporal attention, cross-DOF graph message passing, and multi-task learning with uncertainty-weighted loss. The results show that surge, sway, and yaw can be predicted with high skill scores at model-scale horizons of up to 4 s (32 s full-scale equivalent), while heave and pitch exhibit limited predictability beyond 2 s model scale. The MAC-Net model demonstrates particular advantages for roll prediction, achieving a skill score of 0.88 at a 4 s model-scale horizon compared to 0.76 for the conventional method, attributable to the physical coupling between roll and the horizontal-plane motions through the mooring system. These findings support a practical early warning concept in which horizontal-plane motions provide advance collision alerts and heave/pitch are treated as short-horizon monitoring quantities. Full article

Background/Objectives: Prognostication in ICU patients with documented coma or unresponsiveness is a high-stakes task that informs escalation of care, goals-of-care discussions, and family counselling. Conventional scores are often based on static snapshots and may not reflect early physiological evolution in heterogeneous real-world ICU populations. Routine arterial blood gases (ABG) and SpO₂ are repeatedly measured during early ICU care and may capture clinically meaningful trajectories that can be leveraged by explainable machine learning. To develop and internally validate exploratory, time-updated explainable machine-learning models for ICU outcome in ICU patients with clinically documented coma or unresponsiveness using routine ABG/SpO₂ measurements and physiological trajectories available at admission, 24 h, and 72 h, and to evaluate whether trajectory information adds prognostic information within a staged internal-validation framework. Methods: We conducted a retrospective single-centre study of 108 adult ICU patients with clinically documented coma or unresponsiveness. Predictors included demographics, comorbidity burden, COVID-19 status, baseline ABG/SpO₂ at ICU admission, inflammatory and coagulation biomarkers, and derived ABG/SpO₂ trajectory variables at 24 h and 72 h. Trajectory variables were defined as changes from admission to 24 h and to 72 h and were retained as missing when follow-up measurements were unavailable. The primary ICU-course outcome was ICU death versus transfer to ward. Three staged models were evaluated: Model A using baseline variables, Model B adding 24 h trajectory features, and Model C adding 72 h trajectory features. For each stage, models were analyzed with and without the derived respiratory_support index; models excluding respiratory_support were treated as the main interpretive analyses. Logistic regression, random forest, and gradient boosting (XGBoost) classifiers were assessed using repeated stratified 5-fold cross-validation with 20 repeats and aligned out-of-fold predictions. Performance was reported using AUC-ROC, precision–recall AUC, Brier score, and operating-point metrics; clinical utility was examined with decision-curve analysis. Model interpretation used SHAP and partial dependence plots. Robustness analyses included feature-exclusion sensitivity analysis for respiratory_support and a label-permutation sanity check. Results: ICU mortality was 65.7% (71/108). Follow-up ABG completeness was 75.9% at 24 h and 61.1% at 72 h. Because respiratory_support summarized the highest support level during the first 72 h and strongly separated outcome groups, models excluding respiratory_support were treated as the primary interpretive analyses. In the primary NoRS logistic-regression models, discrimination was moderate-to-strong, with AUC-ROC 0.822 for Model A_noRS, 0.848 for Model B_noRS, and 0.895 for Model C_noRS; bootstrap 95% confidence intervals were 0.739–0.897, 0.766–0.919, and 0.830–0.951, respectively. Measurement-availability sensitivity analyses and simple benchmark models were added to contextualize trajectory-related performance. Respiratory_support-enriched models were retained only as secondary severity-aware analyses, not as admission-only prediction models. Label permutation reduced discrimination toward chance (AUC ≈ 0.55). SHAP and partial-dependence analyses identified oxygenation variables, inflammatory burden, acid–base status, and ΔPaO₂ at 72 h as clinically coherent contributors to predicted risk; when included, respiratory_support dominated feature attribution, consistent with its role as an organ-support intensity marker. Conclusions: In ICU patients with clinically documented coma or unresponsiveness, explainable machine-learning models using routine ABG/SpO₂ trajectories within the first 72 h are feasible and may provide time-updated prognostic information, but the incremental value of trajectory-enriched models over simpler admission-only benchmarks remains unproven. Trajectory-enriched NoRS models retained meaningful discrimination after removing organ-support severity, suggesting a possible physiologically meaningful signal beyond support intensity alone, although definitive incremental value over parsimonious admission-only benchmarks was not established. These findings should be interpreted as exploratory and internally validated only; they do not establish a deployable ICU mortality score, do not demonstrate superiority over established ICU severity scores, and require external validation in larger multicentre cohorts before clinical deployment. Full article

Individual tree species classification is essential for detailed forest inventories, ecosystem monitoring, and biodiversity assessment. While UAV-acquired RGB and multispectral (MS) imagery have advanced tree species mapping, most studies focus on a single sensor type. In practice, UAV platforms carry diverse sensors with varying spatial resolutions, spectral bands, radiometric responses, and noise characteristics, introducing domain shifts that limit model generalization across datasets. To overcome these challenges, we propose a supervised cross-sensor transfer learning approach, leveraging a DenseNet-121 model pretrained on high-resolution UAV RGB imagery to improve classification on lower-resolution multispectral imagery with limited labelled data. The adapted model achieved 75% overall accuracy and a macro-F1 score of 0.706, significantly improving over models trained from scratch. Its performance was further evaluated on downsampled UAV MS imagery simulating conventional airborne multispectral photographs, demonstrating robustness and practical applicability for regional-scale forest inventories. This study highlights cross-domain transfer learning as a pathway toward sensor-independent, efficient, and operationally scalable tree species classification. Full article