17 results about "Urban expansion" patented technology

The invention discloses a city expansion mode recognition method based on algebraic topology and a morphological measure theory, and relates to the technical field of crossing of city planning, geographic information systems and mathematics. Comprising the following steps: constructing a spatio-temporal data cube and a landscape height function, extracting topology invariant features of an urban area by using a continuous coherence algorithm, and generating a persistent graph; then, through calculating generalized curvature measurement and generating a distribution histogram, extracting geometric features of the urban plaque boundary; the topological features and the geometric features are fused to construct a topological-measurement fingerprint; and finally, using a k-nearest neighbor algorithm to classify the city expansion modes in the metric space. According to the method, the dependence of a traditional method on empirical parameters is fundamentally overcome, the method has extremely high tolerance on data noise and form irregularity, and a more powerful and reliable analysis tool is provided for urban expansion mode recognition.

The invention discloses a remote sensing image unsupervised change detection method and system based on structure perception and noise enhancement. According to the method, shared feature representation is extracted from a dual-temporal remote sensing image, a structure perception contrast learning mechanism is introduced to enhance the perception capability of a model for real geographic structure change, noise disturbance consistency constraint is designed to avoid an optimization shortcut problem, and a frequency attention decoding mechanism is adopted to finely depict a change region boundary. The system comprises a preprocessing module, a feature coding module, a structure sensing module, a noise disturbance module, a frequency attention decoding module and an unsupervised optimization module. According to the method, under the condition that manual labeling is not needed, the problems that an existing unsupervised change detection method is short in optimization, insufficient in semantic representation capacity, not fine in boundary description and the like are effectively solved, the accuracy and robustness of change detection are improved, and the method is suitable for the fields of urban expansion monitoring, disaster assessment, environment change analysis and the like.

The invention relates to the technical field of remote sensing image processing, and particularly discloses a dynamic multi-scale change detection method based on ground feature units and change tendency. The innovation point of the invention lies in that a dynamic adaptive scale mechanism of the ground feature unit and the change tendency is constructed, and the change tendency is judged through a three-level fusion mechanism of high-confidence region screening and area weighted statistics, multi-index collaborative judgment and multi-feature clustering. According to the method, the internal scale of a surface feature unit is modulated based on a surface feature unit scale modulation factor of the change tendency, parameters such as weights are dynamically adjusted based on the change tendency, and fine classification combining a multi-statistic threshold value and a hierarchical decision is used, so that the adaptability, classification precision and spatial integrity of change detection in multiple scenes are remarkably improved, and the accuracy of change detection is improved. The method can be widely applied to the fields of land utilization dynamic monitoring, ecological environment evaluation, urban expansion analysis and the like.

Embodiments of the present application provide a method and device for quantifying the stress effect of urban expansion on green space. The method comprises: obtaining urban expansion data and green space data of a plurality of urban areas; the urban expansion data comprises a plurality of urban expansion characteristics, and the green space data comprises a plurality of green space characteristics; clustering the plurality of urban areas according to various green space characteristics in the green space data of the plurality of urban areas; for any one cluster, training a machine learning model using the urban expansion data and the green space data of the urban areas in the cluster to obtain a green space data prediction model corresponding to the cluster; and using an interpreter model to interpret the prediction model to determine the positive and negative and strength of the stress effect of various urban expansion characteristics on green space characteristics under the cluster. In this way, the stress effect of urban expansion on green space can be effectively quantified by combining machine learning and an interpreter.

The invention belongs to the technical field of land resource monitoring, and particularly relates to a land utilization change monitoring method based on deep learning. The monitoring method comprises the following steps: S1, deep learning network training data set selection; S2, deep learning environment configuration; S3, deep learning network training; S4, image prediction; according to the method, a U-Net and DeepLabV3 + semantic segmentation model is selected, a Sentinel-2 satellite image is utilized, a deep learning technology is combined, a land utilization intelligent classification and dynamic monitoring framework is constructed, the land utilization change condition of a research area is monitored, driving factors are analyzed, and the dynamic classification and dynamic monitoring of land utilization are realized. Urban expansion and ecological element space-time evolution rules are revealed by finding out reasons for change of ground feature type proportions, and a scientific basis is provided for territorial space governance; according to the method, the technical advantages of deep learning in high-resolution remote sensing interpretation are verified, and a generalizable normal form is provided for middle city land utilization monitoring.

This application relates to an adaptive path planning method and apparatus for urban wastewater systems. The method includes: collecting target information of the urban wastewater system and determining a set of evolutionary paths that meet preset planning conditions based on the target information; generating a set of candidate schemes for the urban wastewater system based on a coordinated planning scheme for the spatial layout and scale of the urban wastewater system; simulating the renewal and growth process of the urban wastewater system and constructing an adaptive path set for the urban wastewater system based on the adjustment process; planning path planning schemes and paths that meet preset optimal conditions based on average life cycle cost, and executing the path planning schemes and paths that meet the preset optimal conditions. This solves the problem that related urban wastewater system planning technologies can only produce single-stage schemes and cannot consider the adaptation costs to future environmental changes within the system's life cycle, thus failing to support long-term system planning decisions under uncertain conditions such as urban expansion.

The invention discloses a city expansion space-time prediction method and device, computer equipment and a storage medium, and relates to the field of remote sensing time sequence data analysis and geographic space artificial intelligence. The method comprises the following steps: acquiring city expansion data; performing serialization processing and spatio-temporal information embedding on the city expansion data to obtain time series data; inputting the time sequence data into a ViT encoder, and extracting global semantic features; inputting the global semantic features into a CNN decoder, and obtaining pixel-level city expansion prediction corresponding to a specified year; wherein a learnable time embedding vector is introduced into the CNN decoder, and is used for guiding the prediction of a specified year. According to the method, the strong global receptive field of the ViT encoder is utilized to capture long-distance spatial dependence, meanwhile, the CNN decoder is utilized to efficiently reconstruct high-resolution spatial details, in addition, a space-time embedding mechanism is introduced to effectively process complex spatial interaction and time dynamics, and high-precision, long-term and stable prediction is achieved.

This invention provides a method, system, computer equipment, and storage medium for correcting nighttime light remote sensing data, belonging to the field of urban environmental monitoring technology. The method includes: using a multi-source remote sensing sensor to statistically analyze the impermeable and non-impermeable layers in a target area, and calculating a multi-source data consistency index (CI); using the CI to correct the impermeable layer classification results of the target area; and based on the corrected impermeable layer classification results, counting the number N of impermeable layer pixels within the target area. b Number of pixels N in impermeable layer n , using N b and N n Calculate the proportion P of the impermeable layer within a unit pixel. b Using the nighttime light remote sensing brightness value NTL and the proportion of impermeable layer per unit pixel P b A calibration model was constructed to effectively reduce light spillover interference in impermeable areas, significantly improve the accuracy of impermeable layer data, and provide high-precision data support for urban expansion monitoring, light pollution assessment, and socio-economic activity analysis.

The invention provides a city built-up area identification method based on multi-source noctilucent remote sensing data, and relates to the technical field of remote sensing, and the method comprises the steps: obtaining DMSP-OLS and NPP-VIIRS night light data and Landsat remote sensing image data, extracting a normalized water vapor index and a normalized water body index, and carrying out the feature fusion of the extracted water vapor index and normalized water body index with the night light data to obtain corrected light data; with land utilization data as a reference, calculating an optimal threshold value of the corrected light data, identifying an area higher than the threshold value as a city built-up area, and generating a distribution map; and inputting the historical distribution map into a preset space-time diagram neural network model, and outputting a future city built-up area distribution map to predict city expansion. The method effectively reduces the interference of water vapor and water on night light data, improves the recognition accuracy of the urban built-up area, and achieves the dynamic prediction of urban expansion.

The application relates to the technical field of city planning, and discloses a micro-size city expansion measurement method based on a central grid area index, which comprises the following steps: constructing a basic grid, performing step-by-step spatial expansion on the basic grid to form multiple grids of different scales; dividing the research area into uniform grids by using the grids of different scales, then calculating the central grid area index CGAI corresponding to each grid under each scale, and formulating a screening rule based on the central grid area index CGAI, so as to screen the grids, and the remaining grids constitute the CGAI distribution map of the research area corresponding to the grid. The CGAI distribution maps of different scales are reasonably evaluated, and the CGAI distribution map with the highest evaluation result is taken as the final result output.

The invention discloses a remote sensing change detection method for urban expansion monitoring. The method comprises the following steps: step 1, collecting and sorting image samples containing urban expansion change; 2, performing image preprocessing on the images in the data set to enhance data diversity and improve the robustness of the model in a complex scene; 3, performing target labeling on the preprocessed image by adopting a LabelImg labeling tool, and dividing a data set into a training set, a verification set and a test set to ensure that the model can be trained and evaluated on different data sets; step 4, constructing a multi-dimensional feature alignment self-supervising pre-training network MDFANet used for urban expansion monitoring; and 5, inputting the preprocessed and labeled city expansion change data set into the MDFANet model for training, and learning the space and frequency domain features of the city building through forward propagation and reverse optimization, thereby improving the detection precision and generalization ability.

This invention provides a quantitative method for assessing the impact of urbanization expansion patterns on flood factors in small and medium-sized watersheds. This method is based on a coupling of three modules: quantification and clustering identification of urban expansion patterns, cross-validation mechanism of hydrological models and empirical formulas, and a pattern-process response analysis framework. This invention innovatively constructs a comprehensive quantitative index system for urban land use expansion patterns from three dimensions: level, rate, and pattern. By fully utilizing limited rainfall data and watershed geographic information, and through cross-validation using two methods based on different principles, it significantly improves the reliability and accuracy of flood parameter estimation in data-free areas.

The invention provides a noctilucent remote sensing data correction method and system, computer equipment and a storage medium, and belongs to the technical field of urban environment monitoring, and the method comprises the steps: carrying out the statistics of an impervious layer and a non-impervious layer of a target region through a multi-source remote sensing sensor, and calculating a multi-source data consistency index CI; checking an impervious layer classification result of the target area through a multi-source data consistency index CI of the target area; according to the corrected classification result of the impervious layer of the target area, the number Nb of impervious layer pixels and the number Nn of non-impervious layer pixels in the target area are counted respectively, and the proportion Pb of the impervious layer in a unit pixel is calculated through Nb and Nn; a correction model is constructed by using the noctilucent remote sensing brightness value NTL and the impervious layer proportion Pb in a unit pixel, so that light overflow interference of an impervious layer area is effectively reduced, the accuracy of impervious layer data is remarkably improved, and high-precision data support is provided for urban expansion monitoring, light pollution evaluation and social and economic activity analysis.

The application relates to the technical field of remote sensing image processing, and particularly discloses a dynamic multi-scale change detection method based on a ground object unit and a change tendency. The application is characterized in that a dynamic self-adaptive scale mechanism of the ground object unit and the change tendency is constructed, the change tendency is judged through high-confidence-area screening and area-weighted statistics, multi-index collaborative judgment and a multi-feature clustering three-level fusion mechanism, the internal scale of the ground object unit is modulated based on a scale modulation factor of the ground object unit based on the change tendency, parameters such as weights are dynamically adjusted based on the change tendency, and fine classification is achieved by combining a multi-statistical threshold and hierarchical decision-making, so that the adaptability, classification accuracy and spatial integrity of the change detection in multiple scenes are significantly improved, and the application can be widely used in fields such as land use dynamic monitoring, ecological environment evaluation and urban expansion analysis.

The application relates to a city expansion mode recognition method fusing mathematical morphology and landscape connectivity, and belongs to the cross field of city planning and geographic information technology. The method comprises the following steps: recognizing corridor expansion based on road data; recognizing city holes through seed filling and morphological closing operation, and then recognizing infill expansion located in the holes; recognizing enclaves through the calculation of the minimum expansion step number based on eight-neighborhood iterative expansion; and fusing connectivity and linear morphology to recognize corridor expansion and edge expansion. The method provided by the application, namely morphological landscape expansion index MLEI, has significantly improved classification accuracy compared with traditional landscape expansion index LEI, and is suitable for multi-scale city evolution analysis.