Average Precision Values Research Articles

Detection of oscillation-like patterns in eclipsing binary light curves using neural network-based object detection algorithms

The primary aim of this research is to evaluate several convolutional neural network-based object detection algorithms for identifying oscillation-like patterns in light curves of eclipsing binaries. This involved creating a robust detection framework that can effectively process both synthetic light curves and real observational data. The study employs several state-of-the-art object detection algorithms, including Single Shot MultiBox Detector, Faster Region-based Convolutional Neural Network, You Only Look Once, and EfficientDet, as well as a custom non-pretrained model implemented from scratch. Synthetic light curve images and images derived from observational TESS light curves of known eclipsing binaries with a pulsating component were constructed with corresponding annotation files using custom scripts. The models were trained and validated on established datasets, which was followed by testing on unseen Kepler data to assess their generalisation performance. The statistical metrics were also calculated to review the quality of each model. The results indicate that the pre-trained models exhibit high accuracy and reliability in detecting the targeted patterns. The Faster Region-based Convolutional Neural Network and You Only Look Once in particular showed superior performance in terms of object detection evaluation metrics on the validation dataset, including a mean average precision value exceeding 99%. The Single Shot MultiBox Detector, on the other hand, is the fastest, although it shows a slightly lower performance, with a mean average precision of 97%. These findings highlight the potential of these models to significantly contribute to the automated determination of pulsating components in eclipsing binary systems and thus facilitate more efficient and comprehensive astrophysical investigations.

Classification of Pear Varieties Using the K-Nearest Neighbor Algorithm and Extraction of Shape, Color, Texture, and Size Features

This study develops a pear variety classification system based on digital images using the K-Nearest Neighbor (KNN) algorithm. The data used included 195 images from three pear varieties, namely Century, Forel Afrika, and Singo, which were analyzed by utilizing various features such as color (RGB), texture (Local Binary Pattern), shape (area, circumference, length-width ratio), and size (bounding box dimensions). The preprocessing process removes the image's background to increase focus on the main object, thus allowing for more optimal feature extraction. The dataset is divided into 80% for training and 20% for model testing. The evaluation results show that the KNN model can achieve an accuracy of 85%, with an average precision value of 0.85, recall of 0.89, and F1-score of 0.85. These results prove that the KNN algorithm is effective in accurately classifying pear varieties, which can significantly contribute to applying digital image-based technology for automatic classification needs in the agricultural sector.

QuanFormer: A Transformer-Based Precise Peak Detection and Quantification Tool in LC-MS-Based Metabolomics.

In metabolomic analysis based on liquid chromatography coupled with mass spectrometry, detecting and quantifying intricate objects is a massive job. Current peak picking methods still cause high rates of incorrectly picked peaks to influence the reliability and reproducibility of results. To address these challenges, we developed QuanFormer, a deep learning method based on object detection designed to accurately quantify peak signals. Our algorithm combines the feature extraction capabilities of convolutional neural networks (CNNs) with the global computation capability of Transformer architecture. Data training in QuanFormer by using nearly 20,000 annotated regions-of-interest (ROIs) ensures unique prediction via bipartite matching, achieving 96.5% of the average precision value on the test set. Even without retraining, QuanFormer achieves over 90% accuracy in distinguishing true from false peaks. Performance was further analyzed using visualization techniques applied to the encoder and decoder layers. We also demonstrated that QuanFormer could correct retention time shifts for peak alignment and generally surpass the existing methods, including MZmine 3 and PeakDetective, to obtain a larger number of picked peaks and higher accurate quantification. Finally, we also carried out metabolomic analysis in a clinical cohort of breast cancer patients and utilized QuanFormer to detect and quantify the potential biomarkers. QuanFormer is open-source and available at https://github.com/LinShuhaiLAB/QuanFormer.

Detection of Acromion Types in Shoulder Magnetic Resonance Image Examination with Developed Convolutional Neural Network and Textural-Based Content-Based Image Retrieval System.

Background: The morphological type of the acromion may play a role in the etiopathogenesis of various pathologies, such as shoulder impingement syndrome and rotator cuff disorders. Therefore, it is important to determine the acromion's morphological types accurately and quickly. In this study, it was aimed to detect the acromion shape, which is one of the etiological causes of chronic shoulder disorders that may cause a decrease in work capacity and quality of life, on shoulder MR images by developing a new model for image retrieval in Content-Based Image Retrieval (CBIR) systems. Methods: Image retrieval was performed in CBIR systems using Convolutional Neural Network (CNN) architectures and textural-based methods as the basis. Feature maps of the images were extracted to measure image similarities in the developed CBIR system. For feature map extraction, feature extraction was performed with Histogram of Gradient (HOG), Local Binary Pattern (LBP), Darknet53, and Densenet201 architectures, and the Minimum Redundancy Maximum Relevance (mRMR) feature selection method was used for feature selection. The feature maps obtained after the dimensionality reduction process were combined. The Euclidean distance and Peak Signal-to-Noise Ratio (PSNR) were used as similarity measurement methods. Image retrieval was performed using features obtained from CNN architectures and textural-based models to compare the performance of the proposed method. Results: The highest Average Precision (AP) value was reached in the PSNR similarity measurement method with 0.76 in the proposed model. Conclusions: The proposed model is promising for accurately and rapidly determining morphological types of the acromion, thus aiding in the diagnosis and understanding of chronic shoulder disorders.

A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images

Brain tumors present a significant global health challenge, and their early detection and accurate classification are crucial for effective treatment strategies. This study presents a novel approach combining a lightweight parallel depthwise separable convolutional neural network (PDSCNN) and a hybrid ridge regression extreme learning machine (RRELM) for accurately classifying four types of brain tumors (glioma, meningioma, no tumor, and pituitary) based on MRI images. The proposed approach enhances the visibility and clarity of tumor features in MRI images by employing contrast-limited adaptive histogram equalization (CLAHE). A lightweight PDSCNN is then employed to extract relevant tumor-specific patterns while minimizing computational complexity. A hybrid RRELM model is proposed, enhancing the traditional ELM for improved classification performance. The proposed framework is compared with various state-of-the-art models in terms of classification accuracy, model parameters, and layer sizes. The proposed framework achieved remarkable average precision, recall, and accuracy values of 99.35%, 99.30%, and 99.22%, respectively, through five-fold cross-validation. The PDSCNN-RRELM outperformed the extreme learning machine model with pseudoinverse (PELM) and exhibited superior performance. The introduction of ridge regression in the ELM framework led to significant enhancements in classification performance model parameters and layer sizes compared to those of the state-of-the-art models. Additionally, the interpretability of the framework was demonstrated using Shapley Additive Explanations (SHAP), providing insights into the decision-making process and increasing confidence in real-world diagnosis.

MRI to digital medicine diagnosis: integrating deep learning into clinical decision-making for lumbar degenerative diseases.

To develop an intelligent system based on artificial intelligence (AI) deep learning algorithms using deep learning tools, aiming to assist in the diagnosis of lumbar degenerative diseases by identifying lumbar spine magnetic resonance images (MRI) and improve the clinical efficiency of physicians. The PP-YOLOv2 algorithm, a deep learning technique, was used to design a deep learning program capable of automatically identifying the spinal diseases (lumbar disc herniation or lumbar spondylolisthesis) based on the lumbar spine MR images. A retrospective analysis was conducted on lumbar spine MR images of patients who visited our hospital from January 2017 to January 2022. The collected images were divided into a training set and a testing set. The training set images were used to establish and validate the deep learning program's algorithm. The testing set images were annotated, and the experimental results were recorded by three spinal specialists. The training set images were also validated using the deep learning program, and the experimental results were recorded. Finally, a comparison of the accuracy of the deep learning algorithm and that of spinal surgeons was performed to determine the clinical usability of deep learning technology based on the PP-YOLOv2 algorithm. A total of 654 patients were included in the final study, with 604 cases in the training set and 50 cases in the testing set. The mean average precision (mAP) value of the deep learning algorithm reached 90.08% based on the PP-YOLOv2 algorithm. Through classification of the testing set, the deep learning algorithm showed higher sensitivity, specificity, and accuracy in diagnosing lumbar spine MR images compared to manual identification. Additionally, the testing time of the deep learning program was significantly shorter than that of manual identification, and the differences were statistically significant (P < 0.05). Deep learning technology based on the PP-YOLOv2 algorithm can be used to identify normal intervertebral discs, lumbar disc herniation, and lumbar spondylolisthesis from lumbar MRI images. Its diagnostic performance is significantly higher than that of most spinal surgeons and can be practically applied in clinical settings.

An Adaptive Denoising Method for Photon-Counting LiDAR Point Clouds: Application in Intertidal Zones

The intertidal zone, as a dynamic ecosystem at the interface of land and sea, plays a critical role in environmental protection and disaster mitigation. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) is equipped with the Advanced Topographic Laser Altimeter System (ATLAS) with the ability to penetrate the water bodies, enabling its use for bathymetric measurements. However, the complex land cover types and frequent environmental changes in intertidal zones pose significant challenges for precise measurement and dynamic monitoring. In an effort to address the denoising challenges of ICESat-2 photon point cloud data in such complex environments, this study proposes an adaptive photon denoising method that is capable of dynamically adjusting the denoising strategy for different types of photon data. ATL03 data from four typical intertidal zones were selected for denoising experiments. The results indicated that the proposed adaptive denoising method achieved average recall, precision, and F-score values of 0.9885, 0.9927, and 0.9906, respectively, demonstrating excellent denoising performance and stability. This method provides an effective data processing approach for high-precision monitoring of intertidal zone topography.

The Debris Flow Risk Prediction Model Based on PCA-Elman

Accurate prediction of the risk levels of debris flows is crucial for devising effective disaster prevention and mitigation strategies. This study, based on debris flow sample data from Yunnan Province, initially employs Principal Component Analysis to reduce the dimensionality of the raw data, extracting key features and minimizing data dimensions. Subsequently, a 5-fold cross-validation method is utilized to segment the dataset into training and testing sets, and a predictive model integrating Principal Component Analysis with an Elman Neural Network (PCA-Elman) is constructed. The study investigates the impact of data imbalance and spatial variability on the model’s predictive accuracy and attempts to enhance the model’s generalization capabilities by employing the Adaptive Synthetic Sampling algorithm and incorporating samples from unknown regions. The results indicate that the model demonstrates high accuracy and generalization in predicting debris flow risks, with its Area Under Curve value, Average Precision value, and average precision scores surpassing those of traditional models, achieving an accuracy rate of 88.57%. After processing the data with the Adaptive Synthetic Sampling algorithm, the model’s accuracy rate increases to 98.33%. Furthermore, incorporating samples from unknown regions into the trained model significantly improves the prediction accuracy for debris flow risks in those areas. This research offers new insights into the assessment of debris flow hazards and disaster prevention and mitigation efforts, and provides a reference for the construction of predictive models for similar natural disasters.

Enhanced oracle bone corrosion detection using attention-guided YOLO with ghost convolution

Oracle bone inscriptions (OBIs), as the important records of early Chinese characters, possess profound cultural and historical significance. However, These fragments are susceptible to further damage due to corrosion. Consequently, the identification and localization of corroded regions on these fragments to prevent further deterioration has emerged as a critical task. Current object detection algorithms exhibit limitations in identifying corroded regions on oracle bone fragments, which is manifested by suboptimal detection accuracy, F1 scores, and average precision (AP) values. This deficiency hinders their capability to effectively manage the complexity and diversity of corrosion patterns present on oracle bone fragments. To tackle this challenge, this study incorporates advanced attention mechanisms, including Squeeze-and-Excitation Networks (SE), Coordinate attention, and Convolutional Block Attention Module (CBAM), into the YOLOv5 detection architecture. Additionally, we introduce Ghost convolution into the backbone network to effectively retain critical feature map information while optimizing computational efficiency. Our experimental results indicate that the integration of CBAM attention and Ghost convolution within the YOLOv5 backbone markedly improves the detection accuracy of corroded regions on oracle bone fragments. Specifically, compared to the baseline YOLOv5 model, the proposed models incorporating SE, CBAM, and Ghost convolution obtain the improvements of 2.2%, 6.3%, and 8.5% in AP, respectively. This improvement in detection performance not only facilitates the identification of corroded areas but also contributes to the preservation of oracle bone heritage and the continuity of cultural knowledge.

YH-RTYO: an end-to-end object detection method for crop growth anomaly detection in UAV scenarios.

Small object detection via unmanned Aerial vehicle (UAV) is crucial for smart agriculture, enhancing yield and efficiency. This study addresses the issue of missed detections in crowded environments by developing an efficient algorithm tailored for precise, real-time small object detection. The proposed Yield Health Robust Transformer-YOLO (YH-RTYO) model incorporates several key innovations to advance conventional convolutional models. The model features an efficient convolutional expansion module that captures additional feature information through extended branches while maintaining parameter efficiency by consolidating features into a single convolution during validation. It also includes a local feature pyramid module designed to suppress background interference during feature interaction. Furthermore, the loss function is optimized to accommodate various object scales in different scenes by adjusting the regression box size and incorporating angle factors. These enhancements collectively contribute to improved detection performance and address the limitations of traditional methods. Compared to YOLOv8-L, the YH-RTYO model achieves superior performance in all key accuracy metrics, with a 13% reduction in the scale of model. Experimental results demonstrate that the YH-RTYO model outperforms others in key detection metrics. The model reduces the number of parameters by 13%, facilitating deployment while maintaining accuracy. On the OilPalmUAV dataset, it achieves a 3.97% improvement in average precision (AP). Additionally, the model shows strong generalization on the RFRB dataset, with AP50 and AP values exceeding those of the YOLOv8 baseline by 3.8% and 2.7%, respectively.

Disease Segmentation in Purple Sweet Potato Images Using Yolov7

Purple sweet potato is a very important plant in many parts of the world and a major crop in tropical and subtropical climates. Its cultivation can significantly increase production and consumption, and it is beneficial for the nutritional status of people in both rural and urban areas. However, purple sweet potatoes are susceptible to disease outbreaks, which can cause substantial losses to the agricultural industry. To prevent the spread of these diseases and minimize financial losses, it is crucial for farmers to identify purple sweet potato diseases as early as possible. Utilizing deep learning technology to separate areas of purple sweet potatoes marked with disease can effectively address this problem. In this study, researchers employed a segmentation method using the YOLOv7 algorithm. The study's results demonstrated a mean Average Precision (mAP) value of 98.6% from a dataset of 1500 images, divided into two classes: healthy sweet potatoes and diseased sweet potatoes with tuber rot. The mAP value for healthy sweet potatoes was 96.1%, while the mAP for diseased sweet potatoes with tuber rot was 98.6%. The YOLOv7 method, therefore, produces high accuracy values for the segmentation of purple sweet potato diseases. This research significantly contributes to agriculture by enhancing the productivity and quality of sweet potato harvests and can assist farmers in improving the efficiency and sustainability of purple sweet potato production.

A Deep Learning Approach to Plastic Bottle Waste Detection on the Water Surface using YOLOv6 and YOLOv7

Deep learning is a branch of machine learning with many layers, such as the You Only Look Once (YOLO) method. From various versions of YOLO, YOLOv6 and YOLOv7 are considered more prominent because they achieve high Mean Average Precision (mAP) values. Both versions of YOLO have been implemented into various problems, especially in the waste detection problem. Plastic bottle waste is one of the most common types of waste that pollutes Indonesian waters. This study aims to solve this problem by helping to sort waste in surface waters by applying YOLOv6 and YOLOv7. FloW-Img was used, obtained on request from the Orcaboat website. The dataset consists of 500,000 bottle objects in 2,000 images. The YOLOv6 and YOLOv7 models were evaluated using mAP and running time. The results show that YOLOv6 and YOLOv7 can handle bottle waste detection well, with mAP values of 0.873 and 0.512, respectively. In addition, YOLOv6 (4.21 m/s) has a higher detection speed than YOLOv7 (13.7 m/s). However, in tests with images that do not have bottle objects, YOLOv7 provides better detection accuracy and consistency results, making it more suitable for real-world applications that demand high accuracy in environments with much visual noise.

A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection.

Aluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices. In this study, we propose an innovative aluminum surface defect detection method based on an optimized two-stage Faster R-CNN network. A 2D camera serves as the image sensor, capturing high-resolution images in real time. Optimized lighting and focus ensure that defect features are clearly visible. After preprocessing, the images are fed into a deep learning network incorporated with a multi-scale feature pyramid structure, which effectively enhances defect recognition accuracy by integrating high-level semantic information with location details. Additionally, we introduced an optimized Convolutional Block Attention Module (CBAM) to further enhance network efficiency. Furthermore, we employed the genetic K-means algorithm to optimize prior region selection, and a lightweight Ghost model to reduce network complexity by 14.3%, demonstrating the superior performance of the Ghost model in terms of loss function optimization during training and validation as well as in terms of detection accuracy, speed, and stability. The network was trained on a dataset of 3200 images captured by the image sensor, split in an 8:1:1 ratio for training, validation, and testing, respectively. The experimental results show a mean Average Precision (mAP) of 94.25%, with individual Average Precision (AP) values exceeding 80%, meeting industrial standards for defect detection.

Development and Application of Small Object Visual Recognition Algorithm in Assisting Safety Management of Tower Cranes

This study presents a novel video-based risk assessment and safety management technique aimed at mitigating the risk of falling objects during tower crane lifting operations. The conventional YOLOv5 algorithm is prone to issues of missed and false detections, particularly when identifying small objects. To address these limitations, the algorithm is enhanced by incorporating an additional small object detection layer, implementing an attention mechanism, and modifying the loss function. The enhanced YOLOv5s model achieved precision and recall rates of 96.00%, with average precision (AP) values of 96.42% at an IoU of 0.5 and 62.02% across the range of IoU values from 0.5 to 0.95. These improvements significantly enhance the model’s capability to accurately detect crane hooks and personnel. Upon identifying the hook within a video frame, its actual height is calculated using an interpolation function derived from the hook’s dimensions. This calculation allows for the precise demarcation of the danger zone by determining the potential impact area of falling objects. The worker’s risk level is assessed using a refined method based on the statistical analysis of past accidents. If the risk level surpasses a predetermined safety threshold, the worker’s detection box is emphasized and flagged as a caution on the monitoring display.

State-of-the-Art Techniques for Fruit Maturity Detection

For decades, fruit maturity assessment in the field was challenging for producers, researchers, and food supply agencies. Knowing the maturity stage of the fruit is significant for precision production, harvest, and postharvest management. A prerequisite is to detect and classify fruit of different maturities from the background environment. Recently, deep learning technology has become a widely used method for intelligent fruit detection, due to it having higher accuracy, reliability, and a faster processing speed compared with traditional image-processing methods. At the same time, spectral imaging approaches can predict the maturity stage by acquiring and analyzing the spectral data of fruit samples. These maturity detection methods pay more attention to the species, such as apple, cherry, strawberry, and mango, achieving the mean average precision value of 98.7% in apple fruit. This review provides an overview of the most recent methodologies developed for in-field fruit maturity estimation. The basic principle and representative research output associated with the advantages and disadvantages of these techniques were systematically investigated and analyzed. Challenges, such as environmental factors (illumination condition, occlusion, overlap, etc.), shortage of fruit datasets, calculation, and hardware costs, were discussed. The future research directions in terms of applications and techniques are summarized and demonstrated.

Small Object Detection in UAV Remote Sensing Images Based on Intra-Group Multi-Scale Fusion Attention and Adaptive Weighted Feature Fusion Mechanism

In view of the issues of missed and false detections encountered in small object detection for UAV remote sensing images, and the inadequacy of existing algorithms in terms of complexity and generalization ability, we propose a small object detection model named IA-YOLOv8 in this paper. This model integrates the intra-group multi-scale fusion attention mechanism and the adaptive weighted feature fusion approach. In the feature extraction phase, the model employs a hybrid pooling strategy that combines Avg and Max pooling to replace the single Max pooling operation used in the original SPPF framework. Such modifications enhance the model’s ability to capture the minute features of small objects. In addition, an adaptive feature fusion module is introduced, which is capable of automatically adjusting the weights based on the significance and contribution of features at different scales to improve the detection sensitivity for small objects. Simultaneously, a lightweight intra-group multi-scale fusion attention module is implemented, which aims to effectively mitigate background interference and enhance the saliency of small objects. Experimental results indicate that the proposed IA-YOLOv8 model has a parameter quantity of 10.9 MB, attaining an average precision (mAP) value of 42.1% on the Visdrone2019 test set, an mAP value of 82.3% on the DIOR test set, and an mAP value of 39.8% on the AI-TOD test set. All these results outperform the existing detection algorithms, demonstrating the superior performance of the IA-YOLOv8 model in the task of small object detection for UAV remote sensing.

Automatic reconstruction of semantic façade model of architectural heritage

Façade elements, such as windows, doors, balconies, sculptures, and totems, in architectural heritage images with incomplete structures should be automatically reconstructed for applications in 3D analysis, 3D modeling, virtual tourism, city planning, and the protection and reconstruction of architectural heritage. This study segments façade elements of architectural heritage semantically using YOLOv9. A parameterized expression for the semantic façade model is designed. In addition, the façade layer graph (FLG) and element layer graph (ELG) algorithms are developed based on topological, geometric, and structural constraints to automatically reconstruct the semantic façade model for architectural heritages. The results showed that the average precision (AP) and mean intersection over union (MIoU) achieved using YOLOv9 + FLG-ELG are 86.91% and 85.63%, respectively, on the dataset concerning façade elements of architectural heritages. The AP values obtained from the proposed method are 98.5% on the ECP2011 dataset and 95.3% on the Graz2012 dataset. The YOLOv9 + FLG-ELG method automatically reconstructs regular, irregular, and complex façade layouts with high accuracy and robustness.

Can Historical Accident Data Improve Sustainable Urban Traffic Safety? A Predictive Modeling Study

Traffic safety is a critical factor for the sustainable development of urban transportation systems. This study investigates the impact of historical accident information on the prediction of future traffic accident risks, as well as the interaction between this information and other features, such as driver violations and vehicle attributes. Using a comprehensive dataset of traffic accidents involving passenger vehicles in a western Chinese city, we developed two predictive models: Model 1, which is based on vehicle information and driver violations, and Model 2, which integrates historical accident data. The results indicate that the inclusion of historical accident information significantly enhances the predictive performance of the model, particularly in terms of AUC (Area Under the Curve) and AP (Average Precision) values. Furthermore, through feature importance analysis and SHAP (SHapley Additive exPlanations) value evaluation, this study reveals the interaction effects between historical accident data and other features, and how these interactions influence model decisions. The findings suggest that historical accident data play a positive role in predicting future accident risk, with varying effects on risk mitigation. These insights provide a scientific basis for developing strategies to ensure the sustainable development of urban transportation systems.

The Development Mask R-CNN Model for Identification of Melon Plant Leaves and Branches

The quality of melons can be enhanced and optimized by pruning melon plants. Pruning is a removal process carried out on specific parts of the plant. Currently, melon plants are still pruned manually by farmers, but there are many drawbacks to this method. In this research, pruning is conducted on the branches and leaves of melon plants. Pruning can be facilitated with the assistance of a robot capable of recognizing leaves and branches. In this study, the method used to detect branches and leaves is the Mask Region-based Convolutional Neural Network (Mask R-CNN). Hyperparameter tuning technique is employed to obtain the best parameter values, including learning rate, weight decay, and learning momentum. Two scenarios are considered in this research, one with 10 epochs and the other with 30 epochs. The obtained Average Precision (AP) values at 10 epochs are 32.2% for leaf objects and 0% for branches. At 30 epochs, the AP values are 56.8% for leaf objects and 4.1% for branches. The mean Average Precision (mAP) is 16.1% for 10 epochs and 28.4% for 30 epochs.

Time-guided convolutional neural networks for spatiotemporal urban flood modelling

Urban flood modelling is key to understand flood risks and develop effective interventions in flood management. Deep learning (DL), known for its robust and automatic feature extraction capabilities, has been applied for urban flood predictions. However, the hybrid spatiotemporal structure of conventional DL-enabled urban flood models is limited in terms of accuracy and efficiency. To address this gap, this study develops a new DL model guided by time information. This model uses a classic CNN (Convolution Neural Network) architecture, Unet, as its backbone. Time information is integrated into inputs via an extra channel to specify the desired prediction time, facilitating the simulation of the spatiotemporal flood process. Additionally, a modified loss function is formulated to tackle the sample imbalance problem between flooded and non-flooded sites. The model performance is assessed in an urban area in Dalian, China with a total of 18 rainfall events of varying return periods. The model attains average precision and recall values of 0.90 and 0.81, respectively, across different time steps during various events. Furthermore, the model exhibits transferability in ungauged regions where a high influence of surrounding environments on local flood processes is identified by Grad-CAM (Gradient-weighted Class Activation Mapping) analysis. The results show that the new Unet model has great promise in efficiently providing accurate spatiotemporal flood simulations. The time-guided Unet model can serve as practical tools for rapid flood simulation in urban areas.