Search Results (2,380)

Soybean yield prediction is one of the most critical activities for increasing agricultural productivity and ensuring food security. Traditional models often underestimate yields because of limitations associated with single data sources and simplistic model architectures. These prevent complex, multifaceted factors influencing crop growth and yield from being captured. In this line, this work fuses multi-source data—satellite imagery, weather data, and soil properties—through the approach of multi-modal fusion using Convolutional Neural Networks and Recurrent Neural Networks. While satellite imagery provides information on spatial data regarding crop health, weather data provides temporal insights, and the soil properties provide important fertility information. Fusing these heterogeneous data sources embeds an overall understanding of yield-determining factors in the model, decreasing the RMSE by 15% and improving R² by 20% over single-source models. We further push the frontier of feature engineering by using Temporal Convolutional Networks (TCNs) and Graph Convolutional Networks (GCNs) to capture time series trends, geographic and topological information, and pest/disease incidence. TCNs can capture long-range temporal dependencies well, while the GCN model has complex spatial relationships and enhanced the features for making yield predictions. This increases the prediction accuracy by 10% and boosts the F1 score for low-yield area identification by 5%. Additionally, we introduce other improved model architectures: a custom UNet with attention mechanisms, Heterogeneous Graph Neural Networks (HGNNs), and Variational Auto-encoders. The attention mechanism enables more effective spatial feature encoding by focusing on critical image regions, while the HGNN captures interaction patterns that are complex between diverse data types. Finally, VAEs can generate robust feature representation. Such state-of-the-art architectures could then achieve an MAE improvement of 12%, while R² for yield prediction improves by 25%. In this paper, the state of the art in yield prediction has been advanced due to the employment of multi-source data fusion, sophisticated feature engineering, and advanced neural network architectures. This provides a more accurate and reliable soybean yield forecast. Thus, the fusion of Convolutional Neural Networks with Recurrent Neural Networks and Graph Networks enhances the efficiency of the detection process. Full article

Nostalgic scenes can trigger nostalgia to a considerable extent and can be effectively used as a nostalgic trigger that contributes to the psychological comfort of the elderly and immigrant populations, but a design system has not been adequately studied. Therefore, the design principles and digital twin (DT) design system of nostalgic scenes is proposed in this study. It focuses on the construction of a nostalgic scene DT model based on the system of system (SoS) theory. Nostalgic scenes related to farm work are selected and photos of this DT model from a particular perspective are generated for presentation. Co-occurrence analysis is used to verify the correlation between elements within the scene. We invited two groups of residents in Xi’an, the regional group and the non-regional group, a total of 68 people, as participants to rate three photos with different degrees of design on the Likert scale. The results of data analysis show that systematic and well-composed nostalgic scene images, which incorporate relevant elements, are more likely to evoke participants’ nostalgic emotions than ones without those elements mentioned above. Likewise, a series of nostalgic scene images spanning various periods can stimulate participants’ nostalgic emotions more effectively than a single image. Furthermore, region-specific nostalgic scene images that resonate with participants sharing similar lifestyles can trigger their nostalgic feelings more effectively. The digital twin model of the nostalgia scene contains multi-source data, which can be dynamically visualised to represent regional nostalgic experiences. The design system can be used to design nostalgic scenes to improve emotional health, social bonding, tourism, and sustainable urban and rural development. Full article

Accurate and timely air quality forecasting is crucial for mitigating pollution-related hazards and protecting public health. Recently, there has been a growing interest in integrating visual data for air quality prediction. However, some limitations remain in existing literature, such as their focus on coarse-grained classification, single-moment estimation, or reliance on indirect and unintuitive information from visual images. Here we present a dual-channel deep learning model, integrating surveillance images and multi-source numerical data for air quality forecasting. Our model, which combines a single-channel hybrid network consisting of VGG16 and LSTM (named VGG16-LSTM) with a single-channel Long Short-Term Memory (LSTM) network, efficiently captures detailed spatiotemporal features from surveillance image sequences and temporal features from atmospheric, meteorological, and temporal data, enabling accurate time-series forecasting of PM_2.5 and PM₁₀ concentrations. Experiments conducted on the 2021 Shanghai dataset demonstrate that the proposed model significantly outperforms traditional machine learning methods in terms of accuracy and robustness for time-series forecasting, achieving R² values of 0.9459 and 0.9045 and RMSE values of 4.79 μg/m³ and 11.51 μg/m³ for PM_2.5 and PM₁₀, respectively. Furthermore, validation results on the datasets from two stations in Kaohsiung, Taiwan, with average R² values of 0.9728 and 0.9365 and average RMSE values of 1.89 μg/m³ and 5.69 μg/m³ for PM_2.5 and PM₁₀ using a pretrain–finetune training strategy, confirm the model’s adaptability across diverse geographical contexts. These findings highlight the potential of integrating surveillance images to enhance air quality prediction, offering an effective supplement to ground-level environmental monitoring. Future work will focus on expanding datasets and optimizing network architectures to further improve forecasting accuracy and computational efficiency, enhancing the model’s scalability for broader regional air quality management. Full article

The deployment of electric vehicle charging stations (EVCSs) is crucial for the large-scale adoption of electric vehicles and the sustainable energy development of global cities. However, existing research on the spatial distribution of EVCSs has provided limited analysis of spatial equity from the perspective of supply–demand relationships. Furthermore, studies examining the influence of the built environment on EVCS accessibility are scarce, and often rely on single methods and perspectives. To explore the spatial characteristics of EVCS accessibility and its influencing factors, using multi-source urban spatial data, this study initially employs the Gaussian two-step floating catchment area (G2SFCA) method to measure and analyze the spatial distribution characteristics of EVCS accessibility in Guangzhou, China, with consideration of supply–demand relationships. Subsequently, it integrates the MGWR and random forest (RF) models to comprehensively investigate the impact mechanism of the built environment on EVCS accessibility from the perspectives of spatial heterogeneity and non-linear relationship. The results show that the EVCS accessibility exhibits a “ higher in the west and lower in the east, with extreme core concentration” distribution pattern, and has significant spatial autocorrelation. The built-environment variables exhibit different scale effects and spatial non-stationarity, with widespread non-linear effects. Among them, the auto service, distance to regional center, and distance to subway station play important roles in influencing EVCS accessibility. These findings offer important guidance for the efficient and equitable layout of EVCSs in high-density cities. Full article

Accurate land cover mapping plays a critical role in enhancing our understanding of Earth’s energy balance, carbon cycle, and ecosystem dynamics. However, existing methods for producing multi-epoch land cover products still heavily depend on manual intervention, limiting their efficiency and scalability. This study introduces an automated approach for multi-epoch land cover mapping using remote sensing imagery and the model migration strategy. Landsat ETM+ and OLI images with a 30 m resolution were utilized as the primary data sources. An automatic training sample extraction method based on prior multi-source land cover products was first utilized. Then, based on the generated training dataset and a random forest classifier, local adaptive land cover classification models of the reference year were developed. Finally, by migrating the classification model to the target epoch, multi-epoch land cover products were generated. Yuli County in Xinjiang and Linxi County in Inner Mongolia were used as test cases. The classification models were first generated in 2020 and then migrated to 2010 to test the effectiveness of automated land cover classification over multiple years. Our mapping results show high accuracy in both regions, with Yuli County achieving 92.52% in 2020 and 88.33% in 2010, and Linxi County achieving 90.28% in 2020 and 85.28% in 2010. These results demonstrate the reliability of our proposed automated land cover mapping strategy. Additionally, the uncertainty analysis of the model migration strategy indicated that land cover types such as water bodies, wetlands, and impervious surfaces, which exhibit significant spectral changes over time, were the least suitable for model migration. Our results can offer valuable insights for medium-resolution, multi-epoch land cover mapping, which could facilitate more efficient and accurate environmental assessments. Full article

The precise identification of maize kernel varieties is essential for germplasm resource management, genetic diversity conservation, and the optimization of agricultural production. To address the need for rapid and non-destructive variety identification, this study developed a novel interpretable machine learning approach that integrates low-field nuclear magnetic resonance (LF-NMR) with morphological image features through an optimized support vector machine (SVM) framework. First, LF-NMR signals were obtained from eleven maize kernel varieties, and ten key features were extracted from the transverse relaxation decay curves. Meanwhile, five image morphological features were selected using the recursive feature elimination (RFE) algorithm. Before modeling, principal component analysis (PCA) was used to determine the distribution features of the internal components for each maize variety. Subsequently, LF-NMR features and image morphological data were integrated to construct a classification model and the SVM hyperparameters were optimized using an improved differential evolution algorithm, achieving a final classification accuracy of 96.36%, which demonstrated strong robustness and precision. The model’s interpretability was further enhanced using Shapley values, which revealed the contributions of key features such as Max Signal and Signal at Max Curvature to classification decisions. This study provides an innovative technical solution for the efficient identification of maize varieties, supports the refined management of germplasm resources, and lays a foundation for genetic improvement and agricultural applications. Full article

Soil salinization is a serious land degradation phenomenon, posing a severe threat to regional agricultural resource utilization and sustainable development. It has been a mainstream trend to use machine-learning methods to achieve monitoring of large-scale salinized soil quickly. However, machine learning model training requires many samples and hyper-parameter optimization and lacks solvability. To compare the performance of different machine-learning models, this study conducted a soil sampling experiment on saline soils along the south bank of the Yellow River in Dalate Banner. The experiment lasted two years (2022 and 2023) during the spring bare soil period, collecting 304 soil samples. The soil salinity was estimated with the multi-source remote sensing satellite data by combining the extreme gradient boosting model (XGBoost), Optuna hyper-parameter optimization, and Shapley addition (SHAP) interpretable model. Correlation analysis and continuous variable projection were employed to identify key inversion factors. The regression effects of partial least squares regression (PLSR), geographically weighted regression (GWR), long short-term memory networks (LSTM), and extreme gradient boosting (XGBoost) were compared. The optimal model was selected to estimate soil salinity in the study area from 2019 to 2023. The results showed that the XGBoost model fitted optimally, the test set had high R² (0.76) and the ratio of performance to deviation (2.05), and the estimation results were consistent with the measured salinity values. SHAP analysis revealed that the salinity index and topographic factors were the primary inversion factors. Notably, the same inversion factor influenced varying soil salinity estimates at different locations. The saline soils of the study area in 2019 and 2023 were 65% and 44%, respectively, and the overall trend of soil salinization decreased. From the viewpoint of spatial distribution, the degree of soil salinization showed a gradually increasing trend from south to north, and it was most serious on the side near the Yellow River. This study is of great significance for the quantitative estimation of salinized soil in the irrigated area on the south bank of the Yellow River, the prevention and control of soil salinization, and the sustainable development of agriculture. Full article

Accurate estimates of biomass C stocks of grasslands are crucial for grassland management and climate change mitigation efforts. Here, we estimated the mean C stocks of grasslands in the Inner Mongolia Autonomous Region (IMAR), China, in 2020 at a 10 m spatial resolution by combining multi-source data, including remote sensing, climate, topography, soil properties, and field surveys. We used the random forest model to estimate the aboveground biomass (AGB) of grasslands, achieving an R² value of 0.83. We established a relationship between belowground biomass (BGB) and AGB using a power function based on field data, which allows us to estimate the BGB of grasslands from our AGB estimate. We estimated the mean AGB across IMAR to be 100.7 g m⁻², with a total value of 1.4 × 10⁸ t. The BGB of grasslands is much higher than AGB, with mean and total values of 526.0 g m⁻² and 7.4 × 10⁸ t, respectively. Consequently, our C stock estimates show that IMAR grasslands store significantly more C in their BGB (332.6 Tg C) compared to AGB (63.7 Tg C). Random forest model analyses suggested that remotely sensed vegetation indices and soil moisture are the most important predictors for estimating the AGB of grasslands in the IMAR. We highlight the important role of BGB for the C store in the Inner Mongolia grasslands. Full article

Green agriculture represents the future of agricultural transformation in developing countries, such as China. Identifying an effective resource combination path is vital for enhancing the green quality of agriculture in these nations. This study draws on the resource spatial mismatch theory from New Economic Geography, using a “multisource heterogeneous” approach that combines qualitative comparative analysis (QCA) with the EBM-GML index measurement model. Using panel data from 2005 to 2021, the study investigated the effects and mechanisms of spatial resource combinations on improving green agricultural quality. The key findings are as follows: (1) While improving spatial resource misallocation helps boost green agricultural quality, the diversity of resource combination patterns has diminished, decreasing from five modes in 2005 to four in 2021. (2) In terms of mechanisms, reducing externalities, such as pollutant emissions, while strengthening material and human capital offers a potential pathway for improvement. (3) Negative externalities, including emissions from fertilizers and petroleum, significantly hinder improvements in green agricultural quality. (4) The absence of sufficient pesticide and fertilizer resources is a critical factor influencing the outcome. These findings provide practical insights for developing countries seeking to enhance regional resource allocation efficiency and improve agricultural green quality. Additionally, they contribute theoretical support to the enrichment of theories on resource allocation and sustainable agricultural development. Full article

With the continuous advancement of urbanization, urban renewal has become a vital means of enhancing urban functionality and improving living environments. Traditional urban renewal research primarily focuses on the macro level, analyzing regions or units, with limited studies targeting individual buildings. Consequently, the unique characteristics and specific requirements of individual buildings during urban renewal have often been overlooked. This study first identified individual buildings undergoing urban renewal in the Longgang and Longhua Districts of Shenzhen, China, from 2018 to 2023 using multisource data such as the 2018 Shenzhen Building Census. A regression analysis based on building characteristics and locational factors was conducted using a stacking ensemble machine learning model. In addition, buildings were categorized into residential, industrial, and commercial types based on their usage, enabling both overall- and category-specific predictions of building renewal. The results show the following: (1) Using the prediction results of multilayer perceptron (MLP) and eXtreme Gradient Boosting (XGBoost) base models as inputs and fusing them with an AdaBoost classifier as the final metamodel, the goodness of fit of the overall building renewal regression model increased by 2.19%. (2) The regression model achieved an overall urban renewal prediction accuracy of 89.41%. Categorizing urban renewal projects improved the goodness of fit for residential and industrial building renewal by 0.14% and 6.13%, respectively. (3) Compared with traditional macro-level evaluation methods, the experimental results of this study improved by 8.41%, and compared with single-model approaches based on planning permit data, the accuracy improved by 29.11%. Full article

The early prediction of Alzheimer’s disease (AD) risk in healthy individuals remains a significant challenge. This study investigates the feasibility of task-state EEG signals for improving detection accuracy. Electroencephalogram (EEG) data were collected from the Multi-Source Interference Task (MSIT) and Sternberg Memory Task (STMT). Time–frequency features were extracted using the Multitaper method, followed by multidimensional reduction techniques. Subspace features (F24 and F216) were selected via t-tests and False Discovery Rate (FDR) multiple comparisons correction, and subsequently analyzed in the Time–Frequency Area Average Test (TFAAT) and Prefrontal Beta Time Series Test (PBTST). The experimental results reveal that the MSIT task achieves optimal cross-subject classification performance using the Support Vector Machine (SVM) approach with the TFAAT feature set, yielding a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 58%. Similarly, the Sternberg Memory Task demonstrates classification ability with the logistic regression model applied to the PBTST feature set, emphasizing the beta band power spectrum in the prefrontal cortex as a potential marker of AD risk. These findings confirm that task-state EEG provides stronger classification potential compared to resting-state EEG, offering valuable insights for advancing early AD prediction research. Full article

Terraces are an important form of surface modification, and their spatial distribution data are of utmost importance for ensuring food and water security. However, the extraction of terrace patches faces challenges due to the complexity of the terrain and limitations in remote sensing (RS) data. Therefore, there is an urgent need for advanced technology models that can accurately extract terraces. High-resolution RS data allows for detailed characterization of terraces by capturing more precise surface features. Moreover, leveraging deep learning (DL) models with local adaptive improvements can further enhance the accuracy of interpretation by exploring latent information. In this study, we employed five models: ResU-Net, U-Net++, RVTransUNet, XDeepLabV3+, and ResPSPNet as DL models to extract fine patch terraces from GF-2 images. We then integrated morphological, textural, and spectral features to optimize the extraction process by addressing issues related to low adhesion and edge segmentation performance. The model structure and loss function were adjusted accordingly to achieve high-quality terrace mapping results. Finally, we utilized multi-source RS data along with terrain elements for correction and optimization to generate a 1 m resolution terrace distribution map in the Zuli River Basin (TDZRB). Evaluation results after correction demonstrate that our approach achieved an OA, F1-Score, and MIoU of 96.67%, 93.94%, and 89.37%, respectively. The total area of terraces in the Zuli River Basin was calculated at 2557 ± 117.96 km² using EM with our model methodology; this accounts for approximately 41.74% ± 1.93% of the cultivated land area within the Zuli River Basin. Therefore, obtaining accurate information on patch terrace distribution serves as essential foundational data for terrace ecosystem research and government decision-making. Full article

Vector road networks are vital components of intelligent transportation systems and electronic navigation maps. There is a pressing need for efficient and rapid dynamic updates for road network data. In this paper, we propose a series of methods designed specifically for geometric change detection and the topological consistency updating of multi-source vector road networks without relying on complicated road network matching. For geometric change detection, we employ buffer analysis to compare various sources of vector road networks, differentiating between newly added, deleted, and unchanged road features. Furthermore, we utilize road shape similarity analysis to detect and recognize partial matching relationships between different road network sources. For incremental updates, we define topology consistency and propose three distinct methods for merging road nodes, aiming to preserve the topological integrity of the road network to the greatest extent possible. To address geometric conflicts and topological inconsistencies, we present a fusion and update method specifically tailored for partially matched road features. In order to verify the proposed methods, a road central line network with a scale of 1:10000 from the official institution is employed to geometrically update the commercial navigation road network of a similar scale in the remote area. The experiment results indicate that our method achieves an impressive 91.7% automation rate in detecting geometric changes for road features. For the remaining 8.3% of road features, our method provides suggestions on potential geometric changes, albeit necessitating manual verification and assessment. In terms of the incremental updating of the road network, approximately 89.2% of the data can be seamlessly updated automatically using our methods, while a minor 10.8% requires manual intervention for road updates. Collectively, our methods expedite the updating cycle of vector road network data and facilitate the seamless sharing and integrated utilization of multi-source road network data. Full article

During urban development, significant contrasts between urban villages and their surrounding areas lead to the emergence of fragmented urban spaces, dysfunctionalities, cultural barriers, and, ultimately, to the formation of fractured urban textures centered on urban villages (FUT-UVs). The fractured urban textures of an FUT-UV create a disconnect from the surrounding urban area, isolating it from the city. This separation significantly impacts the daily lives and interactions of its residents. To address this and support more sustainable urban development, a thorough and multi-dimensional understanding of FUT-UVs is of crucial importance. This study examines Nanhao Village in Baotou City, conducting a quantitative analysis of key indicators related to buildings, roads, and functional facilities. Using overlay analysis, it explores the characteristics of the FUT-UV, the interactions between these indicators, and opportunities for improvement. From these findings, strategies for reconnecting an FUT-UV with its surroundings are proposed. The results indicate that: (1) FUT-UVs are mainly characterized by low-rise, high-density developments with limited open space. Their road networks are narrow and congested, while accessibility remains low. Low-end businesses are concentrated in a single area within the village, showing minimal functional diversity; (2) FUT-UVs can increase construction intensity by raising the number of floors in buildings, and have higher building densities in the most accessible areas. This increase in density can effectively enhance functional diversity; and (3) improving road accessibility in FUT-UVs will allow for a smoother influx of external activity, enhancing functional diversity. Additionally, increasing the number of building floors intensifies construction, raises the density of functional facilities, and boosts urban vitality. Based on these characteristics of fragmentation and interactive mechanisms, this study suggests stitching strategies related to transportation, architecture, and functionality. This study introduces a new framework for analyzing urban texture, offering a detailed multi-faceted analysis of FUT-UV fragmentation and clarifying the interaction between FUT-UVs and surrounding urban forms. This study reinforces the coherence of the spatial form and the development of the functional economy of urban villages within the modern urban environment. It supports the sustainable development of urban areas and promotes balanced growth between urban villages and their surrounding regions. Full article

Over 30 million people rely on Lake Victoria for survival in Northeast African countries, including Ethiopia, Eritrea, Somalia, and Djibout. The lake faces significant challenges due to changes in land use and climate. This study used multi-source remote sensing data in the Google Earth Engine (GEE) platform to create Land Use and Land Cover (LULC), land surface temperature (LST), and Normalized Difference Water Index (NDWI) layers in the period 2000–2023 to understand the impact of LULC and climate change on Lake Victoria Basin. The land use/land cover trends before 2020 indicated an increase in the urban areas from 0.13% in 2000 to 0.16% in 2020. Croplands increased from 6.51% in 2000 to 7.88% in 2020. The water surface area averaged 61,559 square km, which has increased since 2000 with an average rate of 1.3%. The “Permanent Wetland” size change from 2000 to 2020 varied from 1.70% to 1.83%. Cropland/Natural Vegetation Mosaics rose from 12.77% to 15.01%, through 2000 to 2020. However, more than 29,000 residents were displaced in mid-2020 as the water increased by 1.21 m from the fall of 2019 to the middle of 2020. Furthermore, land-surface temperature averaged 23.98 degrees in 2000 and 23.49 in 2024. Full article