Satellite Data for Environmental Monitoring

BREAKING: Climate data just entered the real-time era 📊 For the first time in history, we now have monthly, independently verified data showing exactly who is polluting, how much, and where. No more pledges. No more greenwashing. No more excuses. Backed by Al Gore, Climate TRACE has launched the world’s first real-time climate emissions dashboard — powered by satellites, sensors, and AI, tracking over 660 million sources. This is like a Bloomberg Terminal for the planet. And it could be the most powerful climate accountability tool ever created. But will the world allow it to reshape the system? Or will vested interests bury it before it can do what it was built to do? I break it down in my latest Forbes article — including insights from COP29, Jay Inslee, and the data that could change everything. 👉 Read the full story: https://lnkd.in/duFxH6P3 #RealTimeClimateData #ClimateTRACE #AlGore #ClimateAction #Forbes #WeDontHaveTime #Transparency #NetZero #GHG #ClimateJustice

📘 Downscaling CHIRPS Precipitation Data to 100m Resolution Using Sentinel-2 in Google Earth Engine Source Code = https://lnkd.in/dNc7NbjE 1. Introduction: Rainfall data at high spatial resolution is critical for precise hydrological analysis, drought monitoring, and agriculture planning. However, most global precipitation datasets, such as CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data), are available at coarser resolutions (~5 km). This project addresses this limitation by downscaling CHIRPS daily precipitation data to 100-meter spatial resolution using bilinear interpolation and Sentinel-2 as a high-resolution spatial reference. 2. Objective: To extract and sum CHIRPS precipitation data over a selected AOI (WMH District) for a specific 3-month period (October 2023 – January 2024). To downscale the CHIRPS raster data to a finer 100-meter resolution using Sentinel-2 spatial referencing. To visualize and compare the original and downscaled precipitation maps. To prepare refined precipitation layers for potential integration with NDVI, crop condition analysis, or drought indices. 3. Importance of the Study: Higher spatial resolution enables more localized analysis of rainfall, especially in heterogeneous landscapes. Improved input for climate models and agro-hydrological studies. Better decision-making for irrigation scheduling, water resource management, and drought preparedness. Supports integration with high-resolution datasets such as NDVI, land use, or soil moisture for multi-parameter environmental studies. 4. Benefits: Enhanced accuracy in rainfall data analysis at local and district levels. Scalable method applicable to any region globally. Supports policymakers and researchers with higher-resolution inputs for climate resilience, agricultural planning, and hydrological monitoring. Efficient use of cloud computing via Google Earth Engine for handling large spatiotemporal datasets. 5. Output: Original CHIRPS Precipitation Map (Oct 2023 – Jan 2024) clipped to WMH District. Downscaled Precipitation Map at 100m resolution, reprojected using Sentinel-2 reference. Color-coded visualization using a 5-class blue gradient, where: Light blue = Low precipitation Dark blue = High precipitation Ready-to-export raster layer of downscaled precipitation (if export added). Output maps can be further used for vegetation correlation (e.g., NDVI vs. rainfall) and SPI generation. #GEE #GoogleEarthEngine #BuildupAreaExpansion #GeospatialAnalytics #RemoteSensing #UrbanExpansion #Geospatial #GoogleEarthEngine #GIS #SustainableDevelopment #Sentinel2 #GeospatialTech #PhD #Agriculture #ClimateSmart #GIS #DeepLearning #ClimateSmartAgriculture #CropHealthMonitoring #DroughtMonitoring #SustainableFarming #Sentinel2 #GoogleEarthEngine #NDVI #LandsatData #GISMapping #GeospatialAnalysis #AIinAgriculture #EarthObservation #AgricultureMapping #RemoteSensin #SatelliteImagery

Did you know the Brazilian National Institute for Space Research (INPE) offers daily precipitation rasters that are calibrated for South America? As we approach the impending El Nino phenomenon in 2023, the reliance on accurate climatological data is more critical than ever. INPE's product, named MERGE, is built upon the IMERGE/GPM model. However, it distinguishes itself by utilizing thousands of in-situ rain gauges to ensure unbiased results. I'm thrilled to share my latest article on #towardsdatascience publication, introducing the merge-downloader package, called Harnessing Precipitation and Climatological Raster Data in South America (https://lnkd.in/dSRJ3jE5) This tool has been specifically designed to simplify the downloading and extraction of time series from this invaluable data. This can be particularly useful for a number of applications such as watershed and reservoir management, critical events monitoring and precision agriculture. Take advantage of this package and enhance your understanding of our changing climate. #datascience #geospatialintelligence #weather #elnino

☁️ Clouds block satellites. Floods don’t care. Here’s how foundation models are being adapted to see through the storm. During extreme weather events like floods, clouds often block optical satellites from capturing usable data. And that's exactly when timely insight matters most. Originally shared by Heather Couture, PhD, this study tackled this head-on. It adapted the Prithvi foundation model, originally trained on optical imagery, by incorporating Synthetic Aperture Radar (SAR) to detect floods across the UK and Ireland. ✅ SAR can “see” through clouds ✅ Fine-tuning the model with SAR bands boosted flood segmentation accuracy from 0.58 to 0.79 ✅ Even small amounts of local data were enough to adapt the model to new regions This research shows that Earth Observation Foundation Models can be effectively adapted for disaster response, even in data scarce areas and how AI can be useful for real world problems. 🌎 I'm Matt and I talk about modern GIS, AI, and how geospatial is changing. 📬 Want more like this? Join 6k+ others learning from my newsletter → forrest.nyc

Orbiting #methane "speed cameras" are catching #oilandgas companies in the act. Satellite images are so clear it's possible to see methane #emissions at the individual asset level. At least two dozen high-resolution satellites are expected to be in orbit by the end of this year. The images sent back are crystal clear and leave little doubt about WHO is responsible for the leaks. These missions will usher in a new era of climate transparency and will help keep oil and gas companies accountable 👏 For example, the image below is of a methane release observed on 5th Feb near Exxon Mobil's Big Eddy Unit 156 that Exxon initially failed to disclose to state officials. After Bloomberg shared the imagery with Exxon, the company notified state regulators. Exxon blamed the omission on "human error" and said "someone forgot to file a form" 🙄 While fines and enforcement vary, companies increasingly face reputational risks and potential loss of business if their operations are seen as contributing more than peers to the climate crisis. Methane has 86x the warming power of carbon dioxide during its first two decades in the atmosphere. Halting emissions of the greenhouse gas could do more to slow climate change in the near-term than almost any other single measure. Facility-level information on emissions is hugely valuable because it's directly actionable. The methane observations are also exposing flaws in decades-old reporting approaches used by companies and government agencies that have typically underestimated emissions. For example, satellite data published earlier this year shows that in the US, methane emissions from oil and gas operations from 2010-2019 were 70% higher than amounts reported by the Environmental Protection Agency. This year could see a wave of new reports on operator leaks, as new orbitals increase the coverage and frequency of observations. For operators unable to halt their emissions, that may mean a loss of credibility, fees or trouble insuring future projects. Fossil fuel companies are running out of places to hide. #energy #sustainability #energytransition #emissionsreduction

Local Weather Data x Critical Risk Management We talk a lot about environmental impacts on high-risk activities—like wind speed & direction impacting crane lifts, work at height, and heavy equipment operations—but how representative is the weather data we rely on? Most of the time, we use forecasted conditions from national meteorological services which are great for general awareness but often don’t reflect site-specific conditions. A forecast from a weather station 30km away doesn’t capture sudden wind gusts at a crane lift zone, temperature variations on-site, or microclimates created by terrain. Having local, real-time weather data at the actual worksite enables better risk management decisions. Instead of relying on broad forecasts, organisations can monitor live conditions at the precise location where critical work is happening. PLUS you get your own comprehensive data set for analytics... In the photos I'm holding a Davis EnviroMonitor Gateway LTE & Vantage Pro2 GroWeather Sensor Suite which is an example of a local weather monitoring system. This system provides real-time, hyper-local weather data directly from the worksite, enabling data-driven risk management decisions. It delivers real-time updates every 2.5 seconds; has wind speed, temperature, humidity, and rainfall monitoring plus solar radiation and evapotranspiration data which is also valuable for heat stress risk. This model has LTE connectivity (basically you can stick a SIM card in it) for remote monitoring and integration with cloud platforms. These systems aren't that expensive and offer new insights for local risk management that I've found can make a pretty big difference to your risk control strategy. Is anyone else implementing local weather systems for crane ops or other critical risk management? #safetytech #safetyinnovation #IoT

𝗪𝗵𝗮𝘁 𝗶𝗳 𝘄𝗲 𝗰𝗼𝘂𝗹𝗱 𝗽𝗶𝗻𝗽𝗼𝗶𝗻𝘁 𝗵𝗼𝘄 𝗺𝘂𝗰𝗵 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗰𝗵𝗮𝗻𝗴𝗲 𝗶𝘀 𝘁𝗼 𝗯𝗹𝗮𝗺𝗲 𝗳𝗼𝗿 𝗲𝘃𝗲𝗿𝘆 𝗲𝘅𝘁𝗿𝗲𝗺𝗲 𝘄𝗲𝗮𝘁𝗵𝗲𝗿 𝗲𝘃𝗲𝗻𝘁? 𝗧𝗵𝗮𝗻𝗸𝘀 𝘁𝗼 𝗖𝗮𝗿𝗯𝗼𝗻𝗕𝗿𝗶𝗲𝗳 - 𝗻𝗼𝘄 𝘄𝗲 𝗰𝗮𝗻! Carbon Brief just released one of the most powerful climate tools I’ve seen in a while: an interactive map of every major extreme weather event where scientists have formally assessed the role of climate change. This latest iteration of the interactive map includes more than 600 studies, covering almost 750 extreme weather events and trends. Because each point on the map tells a story—and about three-quarters of all events mapped end the same way: they were made worse or more likely by human-induced climate change. There were multiple cases where scientists found that an 'extreme-event' was virtually impossible without human influence. Only around 9% of all events were less severe because of climate change. Here are a few insights that stood out to me: ➤ Heatwaves are the clearest signal. They account for more than one-third of studies, and nearly every single one has been intensified by warming. ➤ Many extreme events—like the 2021 Pacific Northwest heat dome—were deemed virtually impossible without climate change. ➤ We need more global equity in climate science. Most attribution studies focus on Europe, North America, and China. Countries most vulnerable to climate extremes—especially in the Global South—are underrepresented. That skews both policy and preparedness. ➤ Attribution science is maturing fast. The field barely existed in 2004. Today, we can assess the climate fingerprints of disasters in near-real time. That’s game-changing for insurers, governments, and risk modelers alike. 𝗠𝘆 𝗧𝗮𝗸𝗲: As someone modelling systemic climate risk for business, I see this dataset as more than academic. It’s a new layer of evidence for scenario analysis, impact forecasting, and portfolio stress testing. But it’s also a reminder that climate change is not a future problem it’s changing our weather 𝘳𝘪𝘨𝘩𝘵 𝘯𝘰𝘸. 𝗜𝗳 𝘆𝗼𝘂’𝗿𝗲 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗿𝗶𝘀𝗸 𝘁𝗼𝗼𝗹𝘀, 𝗮𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻 𝘀𝘁𝗿𝗮𝘁𝗲𝗴𝗶𝗲𝘀, 𝗼𝗿 𝘀𝘂𝘀𝘁𝗮𝗶𝗻𝗮𝗯𝗹𝗲 𝗳𝗶𝗻𝗮𝗻𝗰𝗲 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀—𝘁𝗵𝗶𝘀 𝗺𝗮𝗽 𝗶𝘀 𝗴𝗼𝗹𝗱. 🔗 Explore it here: https://lnkd.in/eyaZES6x #ClimateRisk #ExtremeWeather #AttributionScience #Sustainability #ClimateAction #ScenarioAnalysis #ClimateData #NetZero #Adaptation _____________ For updates on sustainability, climate, and innovation, follow me on LinkedIn: Scott Kelly

So excited to share our new Nature paper on GenCast, an ML-based probabilistic weather forecasting model: https://lnkd.in/enzPUFbn It represents a substantial step forward in how we predict weather and assess the risk of extreme events. 🌪️ GenCast uses diffusion to generate multiple 15-day forecast trajectories for the atmosphere. It assigns more accurate probabilities to possible weather scenarios than the SoTA physics-based ensemble system from ECMWF, across a 2019 evaluation period. It’s vital that we ensure these new ML weather systems are safe and reliable. One thing I'm proud of is our range of evaluation experiments: per-grid-cell skill & calibration, spatial structure, renewable energy, extreme cold/heat/wind, and the paths of tropical cyclones (i.e. hurricanes). For example, we created a dataset of simulated wind power data at wind farm sites across the globe, and found that GenCast outperforms ENS by 10–20% up to 4 days ahead. This is promising, because better weather forecasts can reduce renewable energy uncertainty and accelerate decarbonisation. We also compared cyclone tracks from GenCast and ENS with ~100 cyclones observed in 2019. GenCast's ensemble mean cyclone track has a 12-hour position error advantage over ENS out to 4 days, and more actionable track probability fields out to 7 days. Cyclone maximum wind speeds are still generally underestimated (a common problem for ML weather models), but this performance on tracks is really promising. One recent devastating cyclone was Hurricane Milton, which caused >$85 billion in damages. GenCast predicted ~70% probability of landfall in Florida 8.5 days before the hurricane struck (and ~2 days before it even formed). A GenCast ensemble member takes 8 minutes on a TPU chip, versus hours on a supercomputer for physics-based models. This opens up the possibility of large ensembles (eg 1000s of members) which could better estimate risks of extreme events. We don't yet know how much value this will yield over conventional ensemble sizes (~50 members). Like its predecessor (GraphCast), the weights & code of GenCast have been made publicly available: https://lnkd.in/eg78dd7T. We’re looking forward to seeing how the community builds on this! It's been an honour to work on this study led by Ilan Price with such a talented team ✨: Alvaro Sanchez Gonzalez, Ferran Alet Puig, Andrew El-Kadi, Dominic Masters, Timo Ewalds, Jacklynn Stott, Shakir Mohamed, Peter Battaglia, Rémi Lam, & Matthew Willson

Croatia lost nearly 1% of its forest cover in 8 years. Here's how satellite AI detected the change. GEE’s Dynamic World dataset maps nine land cover types globally - water, trees, grass, crops, built areas - using AI analysis of Sentinel-2 imagery. Updated every 2-5 days at 10-meter resolution, it assigns probability scores to each pixel rather than hard classifications. For this analysis, I focused on the "trees" probability band, processing 1400+ images (2016 and 2024) in  GEE’s cloud to detect forest changes. The entire country-wide analysis took just 10 minutes - no massive data downloads, no local storage limits. I only downloaded final processed results. The results revealed ▶️ 3.2% forest loss vs 2.27% gain, with 34.7% remaining stable. While the AI can miss complex forest patterns or mixed pixels, the dataset's near real-time global coverage unlocks monitoring possibilities previously impossible. You can now track changes across entire countries within days of occurrence. Powerful tool for forestry professionals, environmental consultants, and agencies protecting global forest resources. ▶️ Full R code and methodology: https://lnkd.in/dEc7EZWY ▶️ Learn more about Dynamic World: https://dynamicworld.app #GoogleEarthEngine #DynamicWorld  #ForestManagement #DataScience #SatelliteImagery

🌍 Exploring Daily Precipitation Data Using Google Earth Engine 🌧️ In a recent analysis, I worked on calculating daily precipitation data over the Northeast region of Brazilusing Google Earth Engine. By leveraging satellite data from the TRMM (Tropical Rainfall Measuring Mission), I created a time series for 2019, allowing us to visualize and analyze rainfall patterns over time. This script automates the process of filtering precipitation data, calculating daily sums, and creating a clear visual time series chart. With the increasing need for detailed environmental monitoring, tools like Google Earth Engine make it easier to access, process, and analyze large datasets for environmental research and conservation efforts. 💻 Key steps in the code: Define the area of interest. Filter precipitation data from the TRMM dataset. Calculate daily precipitation totals. Visualize the data in a time series chart. 🌟 Why is this important? Understanding precipitation patterns is critical for monitoring climate change, managing water resources, and protecting ecosystems. This script can be adapted for any region, helping researchers and conservationists gain insights into local and global rainfall trends. 🔗 Explore how to integrate remote sensing into your workflows and make data-driven decisions for a more sustainable future! #GeospatialAnalysis #GoogleEarthEngine #RemoteSensing #EnvironmentalMonitoring #ClimateChange #Conservation #PrecipitationAnalysis #SpatialData #DataScience #GIS #EarthObservation #Sustainability #ResearchAndDevelopment #TRMM #RainfallPatterns See the code bellow: // Define the area of interest (AOI) var roi = ee.FeatureCollection("place your roi here"); Map.centerObject(roi); // Draw the outline of the AOI var empty = ee.Image().byte(); var outline = empty.paint({  featureCollection: roi,  color: 'red',  width: 2 }); Map.addLayer(outline, {palette: ['red']}, 'Roi area'); // Define the start and end dates var startDate = ee.Date('2019-01-01'); var endDate = ee.Date('2022-01-01'); // Define the ImageCollection (TRMM precipitation data) var precipitation = ee.ImageCollection("TRMM/3B42")            .select('precipitation') // Select the precipitation band            .filterDate(startDate, endDate); //**** Daily Data Calculation // Calculate the number of days between the start and end dates var nDays = ee.Number(endDate.difference(startDate, 'day')); print('Number of days:', nDays); // Create a list of sequential days var daysList = ee.List.sequence(0, nDays.subtract(1)); // List of days between start and end dates // Map the list of days to calculate daily precipitation sums var dailyPrecipitationList = daysList.map(function(dayN) {  // Define the start time (t1) for each day  var t1 = startDate.advance(ee.Number(dayN), 'day');    // Define the end time (t2) for each day (one day later)  var t2 = t1.advance(1, 'day');    other parts of the code, down in the comments