Michael Forde’s Post

ARTIFICIAL INTELLIGENCE MEETS CARTOGRAPHY: MAPPING TOOLS CAN CREATE SATELLITE IMAGES FROM TEXT PROMPTS Most people interact with maps regularly, for example, when they're trying to get from point A to point B, track the weather or plan a trip. But beyond those daily activities, maps are also increasingly being combined with artificial intelligence to create powerful tools for urban modeling, navigation systems, natural hazard forecasting and response, climate change monitoring, virtual habitat modeling and other kinds of surveillance. "Maps are a fundamental product in our life," said Aayush Dhakal, a graduate student in the McKelvey School of Engineering at Washington University in St. Louis. "They allow us to learn patterns and see distributions across geospatial area."... #ArtificialIntelligence #Mapping #SatelliteImagery #UrbanModeling #ClimateChange #MachineLearning #RemoteSensing #Cartography #Innovation #CVPR2024 #EarthVision #GenerativeAI #ScientificRouteOÜ https://lnkd.in/dEck6jK7

Satellite Image Processing: Comprehensive Guide to Remote Sensing Unlock the full potential of satellite imagery with this comprehensive guide to satellite image processing and remote sensing. Explore key techniques such as image classification, enhancement, and interpretation using leading tools like QGIS, ArcGIS, and Google Earth Engine. This playlist is perfect for beginners and professionals in GIS, environmental science, and urban planning. Learn how to effectively process satellite images for applications in land use analysis, environmental monitoring, and urban development. 🎥watch the full playlist on YouTube: https://lnkd.in/dcwUYtEq

GeoTIFF: A Deeper Dive into Geo-Referenced Imagery ✨📸 A GeoTIFF (Georeferenced Tagged Image File Format) is a type of raster image file format that includes additional geographical information embedded within the file. GeoTIFF files are commonly used to store georeferenced raster data, such as satellite imagery, aerial photographs, or maps. Here are the key features and components of a GeoTIFF: ✨1-Raster Data: Like a standard TIFF file, a GeoTIFF contains raster data, which is an image composed of a grid of pixels, each with a specific color value. ✨2-Georeferencing Information: What sets GeoTIFF apart is the inclusion of georeferencing metadata. This information provides details about the spatial characteristics of the image, allowing software to accurately position and project the image on the Earth's surface. ✨3-Coordinate System: GeoTIFF includes information about the coordinate system used for the image, specifying how the pixel locations relate to real-world geographic coordinates. This information helps in the proper alignment of the image with geographical features. ✨4-Projection Information: GeoTIFF files often include details about the map projection used, which is essential for transforming the image from its native coordinate system to a standardized map projection. ✨5-Geodetic Datums: Information about the geodetic datum and ellipsoid used for defining the Earth's shape is included in a GeoTIFF. This is crucial for accurate positioning of the image on the Earth's surface. ✨6-Spatial Reference System (SRS): The GeoTIFF may specify a spatial reference system, which is a framework for defining spatial coordinates. GeoTIFF files are widely used in Geographic Information System (GIS) applications, remote sensing, and geospatial analysis. The georeferencing information embedded in a GeoTIFF allows it to be accurately overlaid and integrated with other geospatial datasets, enabling professionals to perform spatial analysis, mapping, and visualization effectively. Image credit: propelleraero.com #3D #GeoTIFF #GeospatialData #GIS #RemoteSensing #MappingMagic #LinkedInLearning

🌍🛰️ Exploring the Power of Temporal Analysis in Satellite Images 🚀📊 Have you ever wondered how satellite images can reveal changes over time? 🌅🌳 In the realm of Earth observation, temporal analysis plays a crucial role in monitoring environmental changes, urban development, agriculture, and more. 🌿🏙️ Join me in unraveling the insights hidden within the evolving landscapes captured by satellites! 🌐💡 See the code bellow: ⚠ you'll need to define a geometry to contain your feature área. // Get MODIS NDVI collection var ndviCollection = ee.ImageCollection('MODIS/006/MOD13A2').select('NDVI'); // Define clipping and region boundary geometries var mask = ee.FeatureCollection('place your feature here'); // Define the regional bounds var region = geometry; // Assuming 'geometry' is defined elsewhere in your code // Group images by composite date var withDOY = ndviCollection.map(function(img) { var doy = ee.Date(img.get('system:time_start')).getRelative('day', 'year'); return img.set('doy', doy); }); var distinctDOY = withDOY.filterDate('2020-01-01', '2021-01-01'); // Define a filter and join to match images by day of year (DOY) var joinFilter = ee.Filter.equals({leftField: 'doy', rightField: 'doy'}); var join = ee.Join.saveAll('doy_matches'); var joinCol = ee.ImageCollection(join.apply(distinctDOY, withDOY, joinFilter)); // Reduce composite groups using median var composite = joinCol.map(function(img) { var doyCol = ee.ImageCollection.fromImages(img.get('doy_matches')); return doyCol.reduce(ee.Reducer.median()); }); // Define visualization parameters var visParams = { min: 0.0, max: 9000.0, palette: [ 'FFFFFF', 'CE7E45', 'DF923D', 'F1B555', 'FCD163', '99B718', '74A901', '66A000', '529400', '3E8601', '207401', '056201', '004C00', '023B01', '012E01', '011D01', '011301' ], }; // Create RGB visualization images var rgbVis = composite.map(function(img) { return img.visualize(visParams).clip(mask); }); // Define GIF visualization parameters var gifParams = { 'region': region, 'dimensions': 600, 'crs': 'EPSG:3857', 'framesPerSecond': 6 }; // Render the animated GIF print(ui.Thumbnail(rgbVis, gifParams)); // Print the GIF URL to the console print(rgbVis.getVideoThumbURL(gifParams)); #SatelliteImagery #TemporalAnalysis #EarthObservation #RemoteSensing #DataAnalysis #GIS #EnvironmentalMonitoring #ClimateInsights #EnvironmentalScience  #ClimateChange #RemoteSensing #EarthObservation  #GoogleEarthEngine #RemoteSensing #DataScience #CodeTutorial #GeospatialAnalysis

Remote sensing and satellite image processing using Earth Observing System (EOS) technology is a crucial aspect of modern geospatial science. I think it is easy than Arcgis tools.

GeoTIFF: A Deeper Dive into Geo-Referenced Imagery ✨📸 A GeoTIFF (Georeferenced Tagged Image File Format) is a type of raster image file format that includes additional geographical information embedded within the file. GeoTIFF files are commonly used to store georeferenced raster data, such as satellite imagery, aerial photographs, or maps. Here are the key features and components of a GeoTIFF: ✨1-Raster Data: Like a standard TIFF file, a GeoTIFF contains raster data, which is an image composed of a grid of pixels, each with a specific color value. ✨2-Georeferencing Information: What sets GeoTIFF apart is the inclusion of georeferencing metadata. This information provides details about the spatial characteristics of the image, allowing software to accurately position and project the image on the Earth's surface. ✨3-Coordinate System: GeoTIFF includes information about the coordinate system used for the image, specifying how the pixel locations relate to real-world geographic coordinates. This information helps in the proper alignment of the image with geographical features. ✨4-Projection Information: GeoTIFF files often include details about the map projection used, which is essential for transforming the image from its native coordinate system to a standardized map projection. ✨5-Geodetic Datums: Information about the geodetic datum and ellipsoid used for defining the Earth's shape is included in a GeoTIFF. This is crucial for accurate positioning of the image on the Earth's surface. ✨6-Spatial Reference System (SRS): The GeoTIFF may specify a spatial reference system, which is a framework for defining spatial coordinates. GeoTIFF files are widely used in Geographic Information System (GIS) applications, remote sensing, and geospatial analysis. The georeferencing information embedded in a GeoTIFF allows it to be accurately overlaid and integrated with other geospatial datasets, enabling professionals to perform spatial analysis, mapping, and visualization effectively. #3D #GeoTIFF #GeospatialData #GIS #RemoteSensing #MappingMagic #LinkedInLearning

🌍🛰️ Exploring the Power of Temporal Analysis in Satellite Images 🚀📊 Have you ever wondered how satellite images can reveal changes over time? 🌅🌳 In the realm of Earth observation, temporal analysis plays a crucial role in monitoring environmental changes, urban development, agriculture, and more. 🌿🏙️ Join me in unraveling the insights hidden within the evolving landscapes captured by satellites! 🌐💡 See the code bellow: ⚠ you'll need to define a geometry to contain your feature área. // Get MODIS NDVI collection var ndviCollection = ee.ImageCollection('MODIS/006/MOD13A2').select('NDVI'); // Define clipping and region boundary geometries var mask = ee.FeatureCollection('place your feature here'); // Define the regional bounds var region = geometry; // Assuming 'geometry' is defined elsewhere in your code // Group images by composite date var withDOY = ndviCollection.map(function(img) { var doy = ee.Date(img.get('system:time_start')).getRelative('day', 'year'); return img.set('doy', doy); }); var distinctDOY = withDOY.filterDate('2020-01-01', '2021-01-01'); // Define a filter and join to match images by day of year (DOY) var joinFilter = ee.Filter.equals({leftField: 'doy', rightField: 'doy'}); var join = ee.Join.saveAll('doy_matches'); var joinCol = ee.ImageCollection(join.apply(distinctDOY, withDOY, joinFilter)); // Reduce composite groups using median var composite = joinCol.map(function(img) { var doyCol = ee.ImageCollection.fromImages(img.get('doy_matches')); return doyCol.reduce(ee.Reducer.median()); }); // Define visualization parameters var visParams = { min: 0.0, max: 9000.0, palette: [ 'FFFFFF', 'CE7E45', 'DF923D', 'F1B555', 'FCD163', '99B718', '74A901', '66A000', '529400', '3E8601', '207401', '056201', '004C00', '023B01', '012E01', '011D01', '011301' ], }; // Create RGB visualization images var rgbVis = composite.map(function(img) { return img.visualize(visParams).clip(mask); }); // Define GIF visualization parameters var gifParams = { 'region': region, 'dimensions': 600, 'crs': 'EPSG:3857', 'framesPerSecond': 6 }; // Render the animated GIF print(ui.Thumbnail(rgbVis, gifParams)); // Print the GIF URL to the console print(rgbVis.getVideoThumbURL(gifParams)); #SatelliteImagery #TemporalAnalysis #EarthObservation #RemoteSensing #DataAnalysis #GIS #EnvironmentalMonitoring #ClimateInsights #EnvironmentalScience #ClimateChange #RemoteSensing #EarthObservation #GoogleEarthEngine #RemoteSensing #DataScience #CodeTutorial #GeospatialAnalysis

.INTRODUCTION IN MAP PROJECTION 3 DOES THE WORLD STILL NEED THE SCIENCE OF MAP PROJECTION!!??? The surface of datum, representing a portion of the globe, may be represented on a plane, i.e. E = fE (φ, λ, a, f) and N = fN (φ, λ, a, f). Where E is easting and N is northing on the classic map of the represent latitude and longitude on the geodetic datum. Representation of a globe surface on a plane must result in some distortions, therefore the properties required of the map projection must be considered The map projections have been discussed in multi thousands of books and papers dating at least from the Claudius Ptolemy time (about AD 150), and projections are known from three centuries earlier. Most of the widely used map projections date from the sixteenth to nineteenth centuries, but many of variations have been modified during the twentieth century. Most map projections may be infinitely differed by choosing many points on the Earth as the center or as a base map point. It can’t be said that there is type best map projection. It is even risky to say that type has found the best projection. A constructed globe map is not the best map for most applications because its map scale is by necessity very small. The earth shape is awkward to use in general, and a ruler can’t be satisfactorily used to measure distance, The question now is why classic map projection is still used if a digital real geodetic map can be developed. This map will be presented using geodetic coordinates directly. The required surveying elements (distances, directions, areas) will be obtained, by push button keys, computed from the geodetic coordinates using computer programs ad joint to the map. The new map will get rid of the noisy distortion. The map can be plotted whenever it is needed. Maps all over the world will be in one mapping system matching the requirements of the non-proceeded satellite gravity missions, satellite positioning (GNSS)and satellite remote sensing imagery.

Fill Gaps in Spatial Data with Spatial Interpolation in Remote Sensing! How do we create smooth, continuous maps from scattered data points? That’s where Spatial Interpolation comes in, predicting unknown values based on known ones to create a complete picture. Let’s dive into some powerful techniques used in image processing and remote sensing: Trend Surface Analysis - Great for seeing broad trends, this method uses a smooth surface to capture general patterns. Inverse Distance Weighting (IDW) - Values closer together are more alike! IDW uses nearby points to estimate unknowns, perfect for clustered data. Global Polynomial - Ideal for large areas, this method fits a polynomial to highlight big-picture patterns without detailed local changes. Kriging - A geostatistical powerhouse, Kriging adapts to both distance and clustering, making it super accurate for complex data. Natural Neighbor - Relies on the closest points around your target, creating a smooth, natural surface for irregular data. Spline Interpolation - Creates smooth curves for a realistic surface, making it ideal for terrain modeling. Each of these techniques has unique strengths, depending on the data and purpose. Ready to learn more about Interpolation Techniques? Read Attached document! 📢 Coming up next: Stay tuned! I’ll cover each of these techniques in detail over the next few days, making it simple, one step at a time! 👉 If this post helped you understand Interpolation in Spatial Data, feel free to repost and share the knowledge! Follow Shehroz Khan and click the 🔔 to stay informed! #GIS #RemoteSensing #Interpolation #ImageProcessing #SpatialAnalysis #GISLearning #Mapping #GISforBeginners

If you ever need to download satellite images and decide to get Landsat images from the USGS website, you'll notice labels like Level 1 (L1) or Level 2 (L2) on the images. You might wonder, what do these mean? These refer to the processing/corrections levels of Landsat satellite images, indicating whether the image has undergone any corrections or preprocessing. At this point, you might ask yourself: What does image correction or preprocessing even mean, and why would satellite images need these corrections? Satellite images often have distortions due to factors that affect their accuracy during acquisition. The most common reasons are: 1. Radiometric Correction This adjustment addresses variations in sensor sensitivity on the satellite, which change over time. Each sensor reacts differently to light, and its sensitivity naturally weakens over the years. Radiometric corrections ensure uniform brightness levels, making images consistent and comparable. 2. Geometric Correction These corrections address geometric distortions caused by: Satellite movement and Earth's rotation. Earth's curvature and terrain features like mountains and valleys. Geometric corrections align the image to a specific map projection, making it geographically accurate. 3. Atmospheric Correction Earth's atmosphere scatters and absorbs sunlight, influenced by particles like dust, water vapor, and gases. This scattering and absorption alter the light reaching the satellite sensor, impacting the image's surface representation. Atmospheric corrections remove these effects, producing more accurate reflectance values. These corrections make Landsat images more reliable and precise, boosting confidence when using them for scientific analyses. Landsat Image Processing Levels 1. Level-0 Raw data directly from the satellite without any processing. The image contains original digital numbers (DN) for each pixel, with no corrections applied. Rarely used due to its complexity and need for extensive preprocessing. 2. Level-1 Includes basic corrections like radiometric and geometric adjustments. Suitable for general analysis and widely used. 3. Level-2 Builds on Level-1 with additional atmospheric corrections to remove effects like haze or light scattering. Preferred for more detailed and precise studies. 4. Levels-3 and 4 Include further processing steps but are less commonly used. For most practical applications, Level-1 and Level-2 are the most popular and are freely available on USGS .