Your cart is empty
Add prompt packs to continue
This definitive collection of prompts for Geographic Information Systems (GIS) represents the most advanced resource for professionals in geomatics, cartography and spatial analysis. Designed with a rigorous technical approach, it allows you to optimize complex workflows, from advanced geoprocessing to satellite remote sensing, guaranteeing millimeter precision in each query and automated process. By integrating these prompts into their work environment, specialists will be able to accelerate decision-making based on geospatial data, solve intricate topological challenges, and master industry-leading tools. It is the ideal strategic investment to convert geographic information into actionable knowledge of high corporate and scientific value.
100 resources included
Acts as a Senior Software Engineer specialized in Geo-processing and Geographic Information Systems (GIS). Your mission is to design and develop a highly optimized and professional script using the [PYTHON_LIBRARY: ArcPy or PyQGIS] library for the automation of advanced geometry manipulation processes. The main objective is to process an input vector layer called [INPUT_LAYER_NAME], which contains entities of type [GEOMETRY_TYPE: Points, Lines or Polygons], and apply a series of chained spatial transformations that allow cleaning, transforming and validating the geographic data for a large-scale infrastructure analysis. The script should begin by implementing rigorous topology validation logic to identify and correct common errors such as self-intersections, null geometries, or spatial duplicates. Once the data has been validated, the execution of a geoprocessing sequence is required that includes: 1) The generation of a dynamic area of influence (buffer) whose distance is determined by the numerical value of the field [FIELD_CRITERIO_DISTANCE]; 2) The clipping of the resulting geometries using a mask layer defined as [LIMITING_MASK_LAYER]; and 3) The simplification of the resulting vertices using the [ALGORITHM_SImplIFICATION: Douglas-Peucker or Wang-Müller] algorithm applying a tolerance of [VALUE_TOLERANCE] to reduce the weight of the file without losing morphological integrity. It is essential that the code follows development best practices, being modular and employing robust exception handling using try-except blocks to catch errors specific to file read or spatial database engines. The script must generate a log file that documents in detail the execution time, the number of entities processed, and any anomalies detected. The final result must be automatically exported to a data container of type [OUTPUT_FORMAT: File Geodatabase, GeoPackage or PostGIS], ensuring that the metadata is preserved and that the coordinate reference system (SRC) is maintained or is obligatorily transformed to the [DESTINATION_SRC: EPSG:XXXX] system. Finally, it optimizes performance for processing large volumes of data (Big Spatial Data) by using quick access cursors ([CURSOR_TYPE: InsertCursor or UpdateCursor]) and, if possible, by taking advantage of parallel processing or multiprocessing techniques. The code must be fully commented in Spanish, explaining the logic behind each geometric transformation and facilitating its future integration into a toolbox or a desktop plugin.
He acts as a Senior Specialist in Remote Sensing and Geospatial Data Analysis with extensive experience in the processing of multispectral images from the Landsat 8/9 and Sentinel-2 programs. Your objective is to provide an exhaustive technical analysis on the discrimination of land covers through the detailed study of their **Spectral Signatures** in the region of [Define Geographic Location] during the period of [Specify Date Range/Season]. The core of your task consists of decomposing the reflective behavior of the following elements: [List elements, e.g.: Native Forest, Corn Crops, Bare Soil, Bodies of Water]. For each element, it describes the theoretical reflectance curve in the Visible (VIS), Near Infrared (NIR) and Shortwave Infrared (SWIR) regions of the spectrum. You must explain how biophysical factors, such as chlorophyll content, leaf cell structure, and moisture content, influence the absorption peaks and troughs detected by the sensor [Specify Sensor: Sentinel-2A or Landsat 8 OLI]. Subsequently, it develops a calculation protocol for specific spectral indices that allow maximizing the separation between classes. It includes detailed formulas and technical justification for the use of indices such as NDVI (Vegetation), NDWI (Water), NBR (Burning Severity) or SAVI (Soil) as relevant to the proposed scenario. Analyzes how the radiometric and spatial resolution of the selected sensor affects the purity of the pixels and the possible presence of mixed spectral signatures in the transition zones or ecotones. Finally, propose an advanced workflow for supervised classification based on machine learning techniques such as Random Forest or Support Vector Machines (SVM). Detail how you would use the spectral signatures extracted from the training areas to calibrate the model and how you would perform cross-validation using a confusion matrix, calculating metrics of overall precision, error of omission, error of commission and the Kappa coefficient to ensure the cartographic reliability of the final product.
He acts as a Senior Engineer in Geographic Information Systems (GIS) and Specialist in Photogrammetry with more than 15 years of experience in cartographic rectification. Your mission is to develop a comprehensive technical protocol for the assignment and validation of Ground Control Points (GCP) applied to an image of type [TIPO_DE_IMAGEN]. The main objective is to transform a raster or analog file without coordinates into an accurate geospatial input under the [SISTEMA_DE_COORDENADAS_DESTINO] reference system, ensuring the topological integrity and metric precision required for high-precision engineering projects. Start the process by describing the selection criteria for the control points. These should be landscape elements that present an unambiguous spatial signature, such as intersections of road infrastructure, corners of permanent structures or pre-existing geodetic landmarks. Explains why the spatial distribution of these points must follow a homogeneous scattering pattern, covering both the perimeter and the center of the [TIPO_DE_IMAGEN] image, and how to avoid clustering of points to prevent local geometric distortions during interpolation. It mathematically defines the error evaluation process. Details how to calculate the Root Mean Square Error (RMSE) for each individual point and the total RMSE of the transformation model. Based on the [SOFTWARE_SIG_UTILIZADO] software, it recommends the most suitable transformation model (Polynomial of order 1, 2 or 3, Thin Plate Spline or Projective) depending on the available [NUMERO_MINIMO_GCP] and the degree of deformation of the original source. You must establish a threshold for the [ERROR_MAXIMO_ADMISIBLE] that determines if a point should be relocated, deleted, or if new field data is required to be captured. It concludes by generating a technical report structure that includes a residual table where the theoretical coordinates are compared to the measurements, and provides a step-by-step guide to perform the 'warping' or final rectification process in [SOFTWARE_SIG_UTILIZADO]. The result should ensure that the final cartographic product is compatible with other vector layers and digital elevation models, allowing multi-temporal spatial analyzes without displacements or scale errors.
Compatible with: