VANI data batch production method based on model builder

Abstract

The invention relates to the technical field of remote sensing data processing, in particular to a VANI data batch production method based on a model builder, and the method comprises the steps: 1, collecting remote sensing data and boundary data of a research area; step 2, EVI data batch preprocessing; step 3, performing batch preprocessing on DNB data; and step 4, carrying out VANI data batch production. The VANI data batch production technology is adopted, the EVI data set and the DNB data set can be read and preprocessed in batches, automatic batch production of the VANI data is achieved, the production efficiency is greatly improved, and it is ensured that the quality of the produced VANI data meets the precision requirement. The model builder is adopted for data production, manual intervention is effectively reduced, the error rate is reduced, and the stability and consistency of the data production process are guaranteed. The production method has high flexibility and expandability, the data production scale can be conveniently adjusted and expanded according to requirements, the method adapts to production tasks of different scales and complexity, and the constantly changing service requirements are met.

Description

Technical Field

[0001] The invention relates to the technical field of remote sensing data processing, and in particular to a VANI data batch production method based on a model builder. Background Art

[0002] Vegetation Adjusted Night-Time Light Index (VANI) is a new index that combines night light remote sensing data and enhanced vegetation index. Through this index, we can study the relationship between regional biodiversity, vegetation coverage and night light intensity, so as to scientifically regulate night light intensity and distribution to maintain or improve regional biodiversity and provide management suggestions for regional ecological protection.

[0003] At present, the calculation of VANI data mainly relies on manual operation, and the operation process mainly involves clipping the study area boundary, data resampling, removing negative values ​​and normalization. Manual operation is mainly suitable for processing a small amount of data. When the data scale is large, the manual operation process will frequently perform environment settings, tool selection and input and output settings, which not only increases the cumbersomeness of the operation, but also is prone to errors. In addition, since the geographic coordinate systems of night light remote sensing data and enhanced vegetation index data are inconsistent, the coordinate systems need to be unified before operation, which undoubtedly further increases the difficulty and workload of the operation.

[0004] It can be seen that when processing large-scale data, calculating VANI data using manual operations faces the challenges of inefficiency and error-proneness. This urgently requires the proposal of a novel batch and automated production method to improve the production efficiency and accuracy of VANI data. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and propose a VANI data batch production method based on a model builder. This method can effectively solve the problems of low data production efficiency, low degree of automation and unstable data quality existing in the prior art when processing large-scale data.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for batch production of VANI data based on a model builder, the specific steps are as follows:

[0008] Step 1: Collect remote sensing data and boundary data of the study area;

[0009] Step 2: EVI data batch preprocessing;

[0010] Step 3: DNB data batch preprocessing;

[0011] Step 4: Batch production of VANI data.

[0012] Preferably, in step 1, the following steps are specifically included:

[0013] Step 1.1, collect long-term remote sensing data of the study area: enhanced vegetation index data and night light radiation data, which are recorded as: EVI (Enhanced Vegetation Index) data and DNB (Day Night Band) data respectively; EVI data is the MOD13A3 dataset in the MODIS (MODerate-resolution Imaging Spectroradiometer) sensor product. EVI data is a monthly synthetic vegetation index dataset with a spatial resolution of 1km, which is mainly used to study vegetation health, land cover and carbon cycle. The DNB data is the monthly synthetic VIIRS VCMCFG night light dataset in the VIIRS (Visible Infrared Imaging Radiometer Suite) sensor product. After cloud-free processing and necessary desaturation processing, the DNB data can detect weaker night light radiation with a spatial resolution of 500m.

[0014] Step 1.2: Collect the vector data of the study area boundary, recorded as: study area boundary.

[0015] Preferably, in step 2, before batch calculating VANI data, batch preprocessing is performed on EVI data, and the specific steps are as follows:

[0016] Step 2.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: EVI data preprocessing;

[0017] Step 2.2, use the Iterate Raster Data tool to batch read the EVI dataset: first, put the EVI dataset in a folder and define the name of this folder as: EVI input data folder; then insert the Raster Iterator tool in the EVI data preprocessing model builder, set the workspace to: EVI input data folder, and set the output raster path and name to obtain the output raster;

[0018] Step 2.3, use the Project Raster tool to transform the coordinate system: transform the EVI output raster obtained in the previous step to ensure that the transformed EVI data and DNB data have the same coordinate system; first set the projection environment, set the capture raster in the processing range to a random DNB raster data in the DNB dataset, and set the pixel size in the raster analysis to be consistent with the DNB data; then, insert the projected raster in the model builder, set the output coordinate system to GCS_WGS_1984, and set the output path and name to obtain the projected raster;

[0019] Step 2.4, use the Extract by Mask tool to clip the raster: In order to extract the area to be studied, it is necessary to clip the raster according to the boundary of the study area. Add the Extract by Mask tool in the model builder, use the boundary of the study area as the mask data, the projected EVI raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask;

[0020] Step 2.5, use the raster calculator to remove negative values: the invalid value of EVI data is -3000, and the valid value range is [-2000,10000], where positive values ​​represent vegetation cover, and negative values ​​usually represent non-vegetation covered areas such as water bodies or clouds, so negative values ​​should be removed; add a raster calculator in the model builder, name it: Remove Negative Values, enter the map algebra expression: Con("Raster after extraction by mask">=0,"Raster after extraction by mask"), set the output raster path and name, and get the raster after removing negative values;

[0021] Step 2.6, use the grid calculator to calibrate the effective interval: After the above processing, the EVI values, especially those in the second quarter, are mostly concentrated in [0,8000]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,8000]; for EVI values ​​greater than 8000, a uniform value of 8000 is assigned; add a grid calculator in the model builder, name it: Extract the effective interval, enter the map algebra expression: Con ("grid after removing negative values" <= 8000, "grid after removing negative values", 8000), set the output grid path and name, and get the grid within the effective interval;

[0022] Step 2.7, use the raster calculator to normalize the EVI: In order to compress the EVI data to the [0,1] interval, it needs to be normalized. Add a raster calculator in the model builder, name it: Normalize, enter the map algebra expression: "raster in the valid interval" / 8000.0, set the output raster path and name, and record the obtained data as the preprocessed EVI;

[0023] After the above operations, a complete EVI data batch preprocessing model can be constructed, and the batch preprocessed EVI data can be obtained by running the model.

[0024] Preferably, in step 3, before batch calculation of VANI data, batch preprocessing of DNB data is required, and the specific steps are as follows:

[0025] Step 3.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: DNB data preprocessing;

[0026] Step 3.2: Use the Iterate Raster Data tool to batch read the DNB dataset: First, place the DNB dataset in a folder and define the folder name as: DNB input data folder; then insert the Raster Iterator tool in the DNB data preprocessing model builder, set the workspace to the DNB input data folder, and set the output raster path and name to obtain the output raster;

[0027] Step 3.3, clip the raster using the Extract by Mask tool: Similar to EVI, in order to extract the area to be studied, the DNB raster needs to be clipped according to the study area boundary. Add the Extract by Mask tool in the model builder, use the study area boundary as the mask data, the projected DNB raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask.

[0028] Step 3.4, use the raster calculator to remove negative values: Use the raster calculator to remove negative values ​​in the DNB raster. Add a raster calculator in the model builder and name it: Remove Negative Values. Enter the map algebra expression: Con("Raster after extraction by mask">=0,"Raster after extraction by mask"), set the output raster path and name, and get the raster after removing negative values.

[0029] Step 3.5, use the grid calculator to calibrate the effective interval: the DNB value interval after the above steps is mostly concentrated in [0,5]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,5]; for DNB values ​​greater than 5, a uniform value of 5 is assigned; add a grid calculator in the model builder, name it: Extract Valid Interval, enter the map algebra expression: Con ("grid after removing negative values" <= 5, "grid after removing negative values", 5), set the output grid path and name, and the obtained data is recorded as the preprocessed DNB;

[0030] After the above operations, a complete DNB data batch preprocessing model can be constructed, and the batch preprocessed DNB data can be obtained by running the model.

[0031] Preferably, in step 4, the specific steps are as follows:

[0032] Step 4.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: Batch Calculation VANI;

[0033] Step 4.2: Batch read EVI and DNB datasets

[0034] First, create a DNB iterative raster data modeler. Since two raster iterators cannot be placed in the same model at the same time, it is necessary to create another model builder named iterative raster data modeler. Add a raster iterator to the model, use the folder storing the preprocessed DNB data as the workspace, and set both the input data and the output data as model parameters.

[0035] Then, return to the batch calculation VANI model, import the iterative raster data modeler, name the input data as the preprocessed DNB data folder, and name the output data as the preprocessed DNB;

[0036] Finally, add a raster iterator to the batch calculation VANI model, set the input data to the preprocessed EVI data folder, and set the output data to the preprocessed EVI;

[0037] Step 4.3: Calculate VANI using the grid calculator

[0038] In the batch calculation VANI model, continue to add a raster calculator tool, named: Calculate VANI, enter the map algebra expression in the raster calculator: (1.0-"preprocessed EVI")*"preprocessed DNB"; execute this tool to obtain VANI raster data with a value range of [0,5], set the output raster path and name, and record the generated raster data as VANI_5;

[0039] Step 4.4: Normalize using the Raster Calculator

[0040] Add a Raster Calculator tool in ModelBuilder, name it Normalize, and enter the map algebra expression "VANI" / 5.0. Execute the tool to get the VANI raster data with a value range of [0,1].

[0041] After the above operations, a complete batch calculation VANI model can be constructed, and running the model can batch produce qualified VANI data.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention adopts VANI data batch production technology, which can batch read and preprocess EVI data sets and DNB data sets, realize the automated batch production of VANI data, greatly improve the production efficiency, and ensure that the quality of the produced VANI data meets the accuracy requirements.

[0044] 2. The present invention adopts a model builder for data production, which effectively reduces human intervention, reduces the error rate, and ensures the stability and consistency of the data production process.

[0045] 3. The present invention reduces dependence on manual labor through automation technology, thereby reducing labor costs; the batch production method fully utilizes computing resources and reduces hardware and energy consumption in the production process.

[0046] 4. The production method of the present invention is highly flexible and scalable, and can easily adjust and expand the scale of data production according to needs, adapt to production tasks of different scales and complexities, and meet ever-changing business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of the present invention;

[0048] Figure 2 Schematic diagram of an EVI data batch preprocessing model in an embodiment of the present invention;

[0049] Figure 3 Schematic diagram of a DNB data batch preprocessing model in an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of a batch calculation VANI model in an embodiment of the present invention;

[0051] Figure 5 This is a diagram of VANI data production results in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the advantages and features of the present invention, thereby making a clearer definition of the protection scope of the present invention. The embodiments described in the present invention are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, a VANI data batch production method based on a model builder, the specific steps are as follows:

[0054] Step 1: Collect remote sensing data and boundary data of the study area

[0055] (1) Collect long-term remote sensing data of the study area: Enhanced Vegetation Index data and night light radiation data, which are recorded as EVI (Enhanced Vegetation Index) data and DNB (Day Night Band) data respectively. EVI data is the MOD13A3 dataset in the MODIS (MODerate-resolution Imaging Spectroradiometer) sensor product. EVI data is a monthly synthetic vegetation index dataset with a spatial resolution of 1km, which is mainly used to study vegetation health, land cover and carbon cycle. DNB data is the monthly synthetic VIIRS VCMCFG night light dataset in the VIIRS (Visible Infrared Imaging Radiometer Suite) sensor product. DNB data has been processed without clouds and necessary desaturation, and can detect weaker night light radiation with a spatial resolution of 500m.

[0056] (2) Collect the vector data of the study area boundary, recorded as: study area boundary.

[0057] Step 2: EVI data batch preprocessing

[0058] Before batch calculating VANI data, batch preprocessing of EVI data is performed as follows:

[0059] (1) Create an empty model builder. Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: EVI Data Preprocessing.

[0060] (2) Use the Iterate Raster Data tool to batch read the EVI dataset. First, place the EVI dataset in a folder and define the name of this folder as: EVI input data folder. Then insert the Raster Iterator tool in the EVI data preprocessing model builder, set the workspace to: EVI input data folder, and set the output raster path and name to obtain the output raster.

[0061] (3) Use the Project Raster tool to transform the coordinate system. Transform the coordinate system of the EVI output raster obtained in the previous step to ensure that the transformed EVI data and DNB data have the same coordinate system. First, set the projection environment, set the capture raster in the processing range to a random DNB raster data in the DNB dataset, and set the pixel size in the raster analysis to be consistent with the DNB data. Then, insert the projected raster in the model builder, set the output coordinate system to GCS_WGS_1984, and set the output path and name to obtain the projected raster.

[0062] (4) Use the Extract by Mask tool to clip the raster. In order to extract the area to be studied, it is necessary to clip the raster according to the boundary of the study area. Add the Extract by Mask tool in the model builder, use the boundary of the study area as the mask data, the projected EVI raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask.

[0063] (5) Use the raster calculator to remove negative values. The invalid value of EVI data is -3000, and the valid value range is [-2000, 10000]. Positive values ​​represent vegetation cover, and negative values ​​usually represent non-vegetation covered areas such as water bodies or clouds, so negative values ​​must be removed. Add a raster calculator in the model builder, name it: Remove negative values, enter the map algebra expression: Con ("Raster after extraction by mask"> = 0," Raster after extraction by mask"), set the output raster path and name, and get the raster after removing negative values.

[0064] (6) Use the raster calculator to calibrate the effective interval. After the above processing, the EVI values, especially those in the second quarter, are mostly concentrated in [0,8000]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,8000]. For EVI values ​​greater than 8000, a uniform value of 8000 is assigned. Add a raster calculator in the model builder, name it: Extract the effective interval, enter the map algebra expression: Con ("raster after removing negative values" <= 8000, "raster after removing negative values", 8000), set the output raster path and name, and get the raster within the effective interval.

[0065] (7) Use the raster calculator to normalize the EVI. In order to compress the EVI data to the [0,1] interval, it needs to be normalized. Add a raster calculator in the model builder, name it: Normalization, enter the map algebra expression: "raster in the valid interval" / 8000.0, set the output raster path and name, and record the obtained data as the preprocessed EVI.

[0066] After the above operations, a complete EVI data batch preprocessing model can be constructed ( Figure 2), running the model can obtain batch preprocessed EVI data. Finally, the effect of preprocessed EVI data is as follows Figure 5 As shown in a.

[0067] Step 3: DNB data batch preprocessing

[0068] Before batch calculating VANI data, batch preprocessing of DNB data is required. The steps are as follows:

[0069] (1) Create an empty model builder. Open the model builder in ArcGIS Pro and create an empty geoprocessor model named: DNB Data Preprocessing.

[0070] (2) Use the Iterate Raster Data tool to batch read the DNB dataset. First, place the DNB dataset in a folder and define the folder name as: DNB input data folder. Then insert the Raster Iterator tool in the DNB data preprocessing model builder, set the workspace to the DNB input data folder, and set the output raster path and name to obtain the output raster.

[0071] (3) Use the Extract by Mask tool to clip the raster. Similar to EVI, in order to extract the area to be studied, the DNB raster needs to be clipped according to the study area boundary. Add the Extract by Mask tool in the model builder, use the study area boundary as the mask data, the projected DNB raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask.

[0072] (4) Use the raster calculator to remove negative values. Use the raster calculator to remove negative values ​​in the DNB raster. Add a raster calculator in the model builder, name it: Remove Negative Values, enter the map algebra expression: Con("Raster after extraction by mask">=0,"Raster after extraction by mask"), set the output raster path and name, and obtain the raster after removing negative values.

[0073] (5) Use the raster calculator to calibrate the effective interval. After the above steps, the DNB numerical interval is mostly concentrated in [0,5]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,5]. For DNB values ​​greater than 5, a uniform value of 5 is assigned. Add a raster calculator in the model builder, name it: Extract Valid Interval, enter the map algebra expression: Con ("Raster after removing negative values" <= 5, "Raster after removing negative values", 5), set the output raster path and name, and the obtained data is recorded as the preprocessed DNB.

[0074] After the above operations, a complete DNB data batch preprocessing model can be constructed ( Figure 3), running the model can obtain batch preprocessed DNB data. Finally, the effect of preprocessed DNB data is as follows Figure 5 As shown in b.

[0075] Step 4: VANI data batch production

[0076] (1) Create an empty model builder. Open the model builder in ArcGIS Pro and create an empty geoprocessor model named Batch Calculation VANI.

[0077] (2) Batch reading of EVI and DNB datasets

[0078] First, create a DNB iterative raster data modeler. Since two raster iterators cannot be placed in the same model at the same time, you need to create another model builder and name it iterative raster data modeler. Add a raster iterator to the model, use the folder where the preprocessed DNB data is stored as the workspace, and set both the input data and the output data as model parameters.

[0079] Then, return to the batch calculation VANI model, import the iterative raster data modeler, name the input data as the preprocessed DNB data folder, and name the output data as the preprocessed DNB.

[0080] Finally, add a raster iterator to the batch calculation VANI model, set the input data to the preprocessed EVI data folder, and set the output data to the preprocessed EVI.

[0081] (3) Calculate VANI using the grid calculator

[0082] In the batch calculation VANI model, add a raster calculator tool named Calculate VANI and enter the map algebra expression (1.0-"preprocessed EVI")*"preprocessed DNB" in the raster calculator. Execute the tool to obtain VANI raster data with a value range of [0,5]. Set the output raster path and name and record the generated raster data as VANI_5.

[0083] (4) Normalization using the raster calculator

[0084] Add a Raster Calculator tool in ModelBuilder, name it Normalize, and enter the map algebra expression "VANI" / 5.0. Execute the tool to get the VANI raster data with a value range of [0,1].

[0085] After the above operations, a complete batch computing VANI model can be constructed ( Figure 4 ), running the model can batch produce qualified VANI data, such as Figure 5 As shown in c.

[0086] In summary, the present invention adopts VANI data batch production technology, which can batch read and preprocess EVI data sets and DNB data sets, realize the automated batch production of VANI data, greatly improve production efficiency, and ensure that the quality of produced VANI data meets the accuracy requirements. The production method of the present invention is highly flexible and scalable, and can easily adjust and expand the scale of data production according to demand, adapt to production tasks of different scales and complexities, and meet changing business needs.

[0087] The description and practice disclosed in the present invention are easy to think and understand for ordinary technicians in the technical field, and several improvements and modifications can be made without departing from the principles of the present invention. Therefore, modifications or improvements made without departing from the spirit of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A VANI data batch production method based on a model builder, characterized in that: The specific steps are as follows: Step 1: Collect remote sensing data and boundary data of the study area; Step 2: EVI data batch preprocessing; Step 3: DNB data batch preprocessing; Step 4: Batch production of VANI data.

2. A method for mass production of VANI data based on a model builder according to claim 1, characterized in that: In step 1, the following steps are specifically included: Step 1.1, collect long-term remote sensing data of the study area: enhanced vegetation index data and night light radiation data, which are recorded as EVI data and DNB data respectively; EVI data is the MOD13A3 dataset in the MODIS sensor product, which is a monthly synthetic vegetation index dataset with a spatial resolution of 1km and is used to study vegetation health, land cover and carbon cycle; DNB data is the monthly synthetic VIIRS VCMCFG night light dataset in the VIIRS sensor product, which has been processed without clouds and necessary desaturation, and can detect weaker night light radiation, with a spatial resolution of 500m; Step 1.2: Collect the vector data of the study area boundary, recorded as: study area boundary.

3. The method for mass production of VANI data based on a model builder according to claim 1, characterized in that: In step 2, before batch calculating VANI data, batch preprocessing of EVI data is performed. The specific steps are as follows: Step 2.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: EVI data preprocessing; Step 2.2, use the Iterate Raster Data tool to batch read the EVI dataset: first, put the EVI dataset in a folder and define the name of this folder as: EVI input data folder; then insert the Raster Iterator tool in the EVI data preprocessing model builder, set the workspace to: EVI input data folder, and set the output raster path and name to obtain the output raster; Step 2.3, use the Project Raster tool to transform the coordinate system: transform the EVI output raster obtained in the previous step to ensure that the transformed EVI data and DNB data have the same coordinate system; first set the projection environment, set the capture raster in the processing range to a random DNB raster data in the DNB dataset, and set the pixel size in the raster analysis to be consistent with the DNB data; then, insert the projected raster in the model builder, set the output coordinate system to GCS_WGS_1984, and set the output path and name to obtain the projected raster; Step 2.4: Clip the raster using the Extract by Mask tool: In order to extract the area to be studied, it is necessary to clip the raster according to the boundary of the study area; Add the Extract by Mask tool in the Model Builder, use the study area boundary as the mask data, the projected EVI raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask; Step 2.5, use the raster calculator to remove negative values: the invalid value of EVI data is -3000, and the valid value range is [-2000,10000], where positive values ​​represent vegetation coverage and negative values ​​represent water bodies or cloud non-vegetation coverage areas, so negative values ​​must be removed; add a raster calculator in the model builder, name it: Remove Negative Values, enter the map algebra expression: Con("Raster after extraction by mask">=0,"Raster after extraction by mask"), set the output raster path and name, and get the raster after removing negative values; Step 2.6, use the grid calculator to calibrate the effective interval: After the above processing, the EVI values, especially the values ​​in the second quarter, are concentrated in [0,8000]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,8000]; for EVI values ​​greater than 8000, a uniform value of 8000 is assigned; add a grid calculator in the model builder, name it: Extract the effective interval, enter the map algebra expression: Con ("grid after removing negative values" <= 8000, "grid after removing negative values", 8000), set the output grid path and name, and get the grid within the effective interval; Step 2.7, use the raster calculator to normalize the EVI: In order to compress the EVI data to the [0,1] interval, it needs to be normalized. Add a raster calculator in the model builder, name it: Normalize, enter the map algebra expression: "raster in the valid interval" / 8000.0, set the output raster path and name, and record the obtained data as the preprocessed EVI; After the above operations, a complete EVI data batch preprocessing model can be constructed, and the batch preprocessed EVI data can be obtained by running the model.

4. The method for mass production of VANI data based on a model builder according to claim 1, characterized in that: In step 3, before batch calculation of VANI data, the DNB data needs to be batch preprocessed. The specific steps are as follows: Step 3.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: DNB data preprocessing; Step 3.2: Use the Iterate Raster Data tool to batch read the DNB dataset: First, place the DNB dataset in a folder and define the folder name as: DNB input data folder; then insert the Raster Iterator tool in the DNB data preprocessing model builder, set the workspace to the DNB input data folder, and set the output raster path and name to obtain the output raster; Step 3.3, clip the raster using the Extract by Mask tool: Similar to EVI, in order to extract the area to be studied, the DNB raster needs to be clipped according to the study area boundary. Add the Extract by Mask tool in the model builder, use the study area boundary as the mask data, the projected DNB raster as the input raster, set the output raster path and name, and obtain the raster after extraction by mask. Step 3.4, use the raster calculator to remove negative values: Use the raster calculator to remove negative values ​​in the DNB raster. Add a raster calculator in the model builder and name it: Remove Negative Values. Enter the map algebra expression: Con("Raster after extraction by mask">=0,"Raster after extraction by mask"), set the output raster path and name, and get the raster after removing negative values. Step 3.5, use the grid calculator to calibrate the effective interval: the DNB value interval after the above steps is concentrated in [0,5]. Therefore, in order to make the data at other times also concentrated in this interval, the effective interval needs to be calibrated to [0,5]; for DNB values ​​greater than 5, a uniform value of 5 is assigned; add a grid calculator in the model builder, name it: Extract Valid Interval, enter the map algebra expression: Con ("grid after removing negative values" <= 5, "grid after removing negative values", 5), set the output grid path and name, and the obtained data is recorded as the preprocessed DNB; After the above operations, a complete DNB data batch preprocessing model can be constructed, and the batch preprocessed DNB data can be obtained by running the model.

5. The method for mass production of VANI data based on a model builder according to claim 1, characterized in that: In step 4, the specific steps are as follows: Step 4.1, create an empty model builder: Open the model builder in ArcGIS Pro software and create an empty geoprocessor model named: Batch Calculation VANI; Step 4.2: Batch read EVI and DNB datasets First, create a DNB iterative raster data modeler. Since two raster iterators cannot be placed in the same model at the same time, it is necessary to create another model builder named iterative raster data modeler. Add a raster iterator to the model, use the folder storing the preprocessed DNB data as the workspace, and set both the input data and the output data as model parameters. Then, return to the batch calculation VANI model, import the iterative raster data modeler, name the input data as the preprocessed DNB data folder, and name the output data as the preprocessed DNB; Finally, add a raster iterator to the batch calculation VANI model, set the input data to the preprocessed EVI data folder, and set the output data to the preprocessed EVI; Step 4.3: Calculate VANI using the grid calculator In the batch calculation VANI model, continue to add a raster calculator tool, named: Calculate VANI, enter the map algebra expression in the raster calculator: (1.0-"preprocessed EVI")*"preprocessed DNB"; execute this tool to obtain VANI raster data with a value range of [0,5], set the output raster path and name, and record the generated raster data as VANI_5; Step 4.4: Normalize using the Raster Calculator Add a Raster Calculator tool in ModelBuilder, name it Normalize, and enter the map algebra expression "VANI" / 5.

0. Execute the tool to get the VANI raster data with a value range of [0,1]. After the above operations, a complete batch calculation VANI model can be constructed, and running the model can batch produce qualified VANI data.

Images