Conservation Data Analysis

🌱 How much carbon is your forest storing? The numbers might surprise you! I’m excited to share insights from my latest carbon sequestration mapping project in the mountainous regions of Gilgit-Baltistan. Using ArcGIS, Google Earth Engine (GEE), and Python, we transformed satellite data into actionable intelligence for climate resilience. Key takeaways: Total Carbon Stored: 12,500 tCO₂ High-Impact Zones: Areas identified for targeted conservation Tools Used: GeoAI, raster analysis, GEE cloud processing By visualizing carbon density across landscapes, we can help policymakers prioritize conservation, track ecosystem health, and support climate action. This project reflects how geospatial technologies are driving environmental solutions. 💬 I’d love to hear from the GIS & environmental community: How are you using geospatial tools for climate resilience? What innovative methods have you applied for carbon mapping or environmental monitoring? Let’s share knowledge and turn data into impact! #GIS #RemoteSensing #GeoAI #CarbonMapping #EnvironmentalMonitoring #ClimateTech #Sustainability #FloodMapping #EarthObservation #GEE #Python #ArcGIS #ClimateAction

🌳 Mapping Deforestation Risk with Google Earth Engine: Insights from 30 Years of Satellite Data 🌍 Harnessing the power of Landsat imagery and the JNR Risk Mapping methodology (Verra, 2021), I analyzed forest cover changes in our study area from 1990-2025. Here's what we found: 🔍 Key Findings: 2025 Forest Area: 423,765 Ha (20% decrease since 1990) 1990 Forest Area: 531,321 Ha Annual Deforestation Rate: -0.75% (1990-2025) 🛠 Technical Approach: Multi-Temporal Composites: Combined Landsat 4-9 data with cloud masking Spectral Analysis: Used SWIR-NIR ratio (VI > 0.7) to identify forests Risk Modeling: Created temporal deforestation masks (1990-2005 & 2005-2025) Developed 9x9 kernel convolution for risk propagation Classified risk levels using gradient scaling (0-30) 🌐 Conservation Implications: Red Areas: Historical deforestation hotspots Yellow Zones: Recent loss areas needing monitoring Green Regions: Priority conservation targets This analysis demonstrates how remote sensing can transform environmental management. The risk map helps prioritize interventions and supports carbon stock protection strategies.

Calling all conservation and AI enthusiasts! I’m excited to share our latest paper in Conservation Biology: "Automating the analysis of public saliency and attitudes toward biodiversity from digital media." As the need to monitor Global Biodiversity Framework targets grows, so does the challenge of tracking public sentiment at scale. Conventional surveys are costly and limited, while digital data—though rich—is often cluttered with irrelevant "noise" (e.g., sports teams like the Clemson Tigers vs. actual wildlife). To solve this, we developed a new natural language processing (NLP) pipeline that automates the monitoring of wildlife perceptions globally. Key innovations of our approach: Folk Taxonomy Mapping: We use a human-in-the-loop method to group species based on common name endings (e.g., "sea lion" or "horseshoe bat"), better reflecting how the general public actually discusses wildlife. Zero-Shot Relevance Filtering: We leverage a zero-shot Large Language Model (LLM) to filter out non-biological content without the need for time-consuming manual data annotation. High Performance: Our relevance filter achieved an overall F1 score of 85.8%, effectively triaging massive datasets from news and social media. Why it matters: We applied this method to track public discourse on bats, pangolins, elephants, and gorillas during the COVID-19 pandemic. We found significant shifts in sentiment and volume—for instance, news mentioning horseshoe bats increased nearly sevenfold in early 2020—demonstrating how this tool can track real-world impacts on public perception in real-time. This pipeline offers a practical, scalable way for conservationists to analyze how their outreach or global events are shifting the needle on biodiversity awareness. Read the full open-access paper here: https://lnkd.in/eBJs3HMD #ConservationBiology #NLP #ConservationCulturomics #Biodiversity #DataScience #LLM #ConservationSocialScience

🌍 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

🌍 Integrating Cloud-Based Remote Sensing and Machine Learning for Land-Cover Classification and Disturbance Analysis. This work demonstrates an integrated geospatial workflow aimed at characterizing land-use/land-cover (LULC) patterns and spatial disturbance dynamics using satellite-derived datasets and machine learning techniques. Multispectral data from Google Earth Engine (GEE) were accessed and processed within the R environment, where supervised classification was conducted using Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Trees (CART) algorithms. To enhance classification reliability, the ESA WorldCover product was employed as a reference dataset for generating training samples, enabling improved thematic accuracy and reducing uncertainty in heterogeneous landscapes. The resulting workflow illustrates the utility of cloud-based remote sensing in conjunction with statistical learning methods for: ✔ detecting anthropogenic and environmental disturbance gradients, ✔ quantifying spatial heterogeneity in land-use systems, and ✔ supporting scalable environmental monitoring and assessment efforts. As the impacts of land-use change and climate variability intensify, such integrative approaches provide essential data-driven insights for ecosystem management, conservation planning, and policy formulation. Advancing remote sensing research through open-access EO platforms and reproducible analytical pipelines remains critical for improving LULC characterization and biodiversity-informed decision-making. #RemoteSensing #EarthObservation #MachineLearning #GoogleEarthEngine #RStats #WorldCover #LandUseLandCover #EnvironmentalMonitoring #GeospatialAnalysis #SustainabilityScience #SpatialModeling

𝐀𝐫𝐞 𝐰𝐞 𝐩𝐫𝐨𝐭𝐞𝐜𝐭𝐢𝐧𝐠 𝐚𝐧𝐝 𝐫𝐞𝐬𝐭𝐨𝐫𝐢𝐧𝐠 𝐧𝐚𝐭𝐮𝐫𝐞 𝐢𝐧 𝐭𝐡𝐞 𝐦𝐨𝐬𝐭 𝐢𝐦𝐩𝐚𝐜𝐭𝐟𝐮𝐥 𝐩𝐥𝐚𝐜𝐞𝐬? Most frameworks optimize for one goal at a time: biodiversity, carbon, or water. In our new paper in 𝙀𝙖𝙧𝙩𝙝'𝙨 𝙁𝙪𝙩𝙪𝙧𝙚  (led by Camilo Alejo and Damon Matthews) we use #AI to guide a more integrated approach. We identify where biodiversity, carbon, and water priorities align, and where trade-offs are unavoidable. 𝐘𝐨𝐮 𝐜𝐚𝐧 𝐟𝐢𝐧𝐝 𝐭𝐡𝐞 𝐟𝐮𝐥𝐥 𝐚𝐫𝐭𝐢𝐜𝐥𝐞 𝐡𝐞𝐫𝐞: 👉https://lnkd.in/g8QQYw4s 𝐖𝐡𝐚𝐭 𝐀𝐈 𝐞𝐧𝐚𝐛𝐥𝐞𝐬: • Simultaneous analysis of species habitat connectivity, carbon storage, and water stability at scale • Identification of conservation and restoration priorities aligned with Canada’s 30x30 targets • Explicit mapping of trade-offs—not just synergies 𝐖𝐡𝐚𝐭 𝐰𝐞 𝐟𝐢𝐧𝐝: •Protecting threatened species alongside irrecoverable carbon in forests is the highest-leverage conservation strategy. •Restoration is more complex then protection, requiring targeted strategies across landscapes, with trade-offs that often can't be avoided. •Mining is the fastest-growing threat to priority areas over the next decade. Thank you to Camilo Alejo and Damon Matthews Andréa Ventimiglia, Maria Isabel Arce Plata for your leadership and collaboration on this work. #AI #Nature #climate #NbS #water

Sharing my latest work on mangrove and coastal conservation I’m excited to share the Google Earth Engine code I developed to predict mangrove canopy cover using NDVI and EVI. This workflow applies three machine learning models, Random Forest, SmileGradientTreeBoost, and SmileChart to generate accurate canopy cover predictions. This analysis supports my role as a staff member responsible for calculating the mangrove conservation zone in Middle Tapanuli. Field Data Source The ground-truth data used in this model comes from mangrove canopy cover measurements that I collected in Middle Tapanuli Regency, North Sumatra Province, during 10–20 November 2025. GEE Script Full code available here: https://lnkd.in/gC5SnyTd I hope this resource can support researchers and practitioners working on mangrove monitoring, coastal conservation, spatial planning, and remote sensing applications. Feel free to use or adapt the script, and I’d be happy to connect and collaborate. #RemoteSensing #Mangrove #GoogleEarthEngine #MachineLearning #CoastalEcosystem #GIS #NDVI #EVI #EnvironmentalMonitoring #ConservationZone

Assessing urban tree cover using Sentinel-2A satellite data 🌳🛰️ #GreenCities #RemoteSensing #UrbanForests Tracking land conversion with Sentinel satellite data (2020-2024) 🛰️🌍 Remote sensing offers a powerful, accurate, and large-scale view of environmental changes, helping us understand urban growth, deforestation, and ecosystem shifts. The insights are crucial for sustainable planning and conservation! Step by step: 1️⃣ Data Acquisition 🛰️ • Collect Sentinel-2A/B satellite imagery from ESA’s Copernicus Open Access Hub. • Select images covering the study area from 2020 to 2024. • Apply cloud masking techniques to remove atmospheric disturbances. 2️⃣ Preprocessing 🔍 • Convert raw satellite images to reflectance values. • Apply geometric and radiometric corrections. • Use NDVI, NDBI, and other indices to enhance land cover features. 3️⃣ Land Cover Classification 🏙️🌿 • Apply machine learning (e.g., Random Forest, SVM) or deep learning models for classification. • Use supervised classification techniques with training datasets. • Categorize land types (urban, forest, water, agriculture, barren land). 4️⃣ Change Detection Analysis 🔄 • Compare classified images from different years (2020 vs. 2024). • Identify areas of deforestation, urban expansion, and land degradation. • Quantify changes in land cover percentages. 5️⃣ Validation & Accuracy Assessment ✅ • Use ground truth data and validation points. • Calculate accuracy metrics (confusion matrix, Kappa coefficient). • Refine classification model if needed. 6️⃣ Mapping & Visualization 🗺️ • Generate thematic maps for stakeholders. • Use GIS platforms (QGIS, ArcGIS) to present results. • Create interactive dashboards for decision-makers. 7️⃣ Insights & Decision Support 📊 • Provide reports and analytics on land conversion trends. • Offer recommendations for sustainable land management. • Support urban planning, forestry, and conservation efforts. 🔹 Results Impact: The analysis helps governments, businesses, and environmental agencies make data-driven decisions for sustainable development and resource management. #RemoteSensing #LandUseChange #GISMapping #SatelliteData #UrbanPlanning #EnvironmentalMonitoring #SustainableDevelopment #GeospatialAnalysis #EarthObservation #ClimateAction #Geolux #MappingSolutions #LandManagement #EcosystemMonitoring #RemoteSensing #LandUseChange #GISMapping #SatelliteData #EnvironmentalMonitoring #UrbanPlanning #Forestry #Deforestation #SmartCities #SustainableDevelopment #GeospatialAnalysis #EarthObservation #ClimateAction #PrecisionAgriculture #Geolux #MappingSolutions #LandManagement #EcosystemMonitoring #InfrastructurePlanning

ArchAI, established in 2020 and headquartered in London, UK, specializes in leveraging artificial intelligence to analyze historical and environmental data, primarily focusing on uncovering "lost habitats." Their flagship product, Lost Habitats, utilizes AI to process historical maps and contemporary environmental data, providing insights into the evolution of various UK habitats, including woodlands, wetlands, and pastures. This tool aids conservationists, land managers, and developers in identifying and restoring degraded ecosystems, supporting initiatives like Biodiversity Net Gain (BNG). The company has successfully collaborated with organizations such as the Forestry Commission, National Trust, Natural England, and the University of Southampton. These partnerships have facilitated projects that enhance habitat restoration and inform land management decisions across the UK. ArchAI's innovative approach has garnered recognition, with features in prominent media outlets like BBC and The Guardian. Their AI-driven solutions are transforming how historical data informs environmental conservation and land development strategies. ArchAI’s technology uses artificial intelligence to analyze historical maps and environmental data to uncover lost habitats. The platform primarily processes large datasets, such as old maps, aerial imagery, and contemporary environmental data, using machine learning models to extract key insights. Here’s how it works: 1️⃣Data Collection: The platform collects historical maps, archival records, and modern geospatial data, focusing on landscape features like woodlands, wetlands, and pastures. 2️⃣AI Processing: ArchAI uses machine learning algorithms to analyze these datasets. The algorithms identify patterns and changes over time, particularly in how landscapes have evolved. By comparing historical and modern maps, the AI identifies lost or degraded habitats that may have existed in the past. 3️⃣Geospatial Integration: ArchAI integrates its findings with GIS (Geographic Information Systems) tools, allowing users to visualize changes in the landscape, including areas that may have been restored or are in need of restoration. 4️⃣Insight Generation: The AI identifies key regions that require attention for conservation and restoration efforts, providing detailed insights for land managers, conservationists, and developers. ==**== Discover how ArchAI can revolutionize your conservation efforts. 🔗 Share your thoughts or experiences below! 💬 Comment, follow us for updates, and join the conversation on leveraging AI for a sustainable future!

How can artificial intelligence help biodiversity and nature conservation efforts? Amidst the hype, there is a very important and exciting role for #AI to help conservation efforts that I hope will flourish. There are key strengths to generative predictive transformers and machine learning that can be directly applied to #biodiversity conservation, such as: 1️⃣ Significantly cutting down the time it takes to process data from various data monitoring sources such as acoustics, imaging, eDNA and remote sensing; 2️⃣ Interpreting data from all these sources and helping to digest for non-experts; 3️⃣ Help automate data collection and interpretation, including on-site data collected by ecologists and local communities; 4️⃣ Predict species interactions and migrations; 5️⃣ Predict declines and tipping points for biodiversity; 6️⃣ Helping to adapt to changing climate change scenarios on biodiversity; 7️⃣ Identifying priority areas for conservation and restoration based on dynamic data and within budgetary constraints; 8️⃣ Predicting future deforestation and/or poaching. (Some links for further reading in the comments) 🧪 Already, experiments like CAPTAIN (Conservation Area Prioritization Through Artificial INtelligence) have demonstrated the effectiveness of reinforced learning to identify priority conservation areas. 🌴 Predicting deforestation is also a key area. According to WWF, which has piloted a project called ‘Forest Foresight’ in Borneo and Gabon, AI can predict forest loss up to six months out with 80% accuracy. ⚠️ There are some blind spots to be aware of, such as assuming AI will solve all our problems for us; data inequities, with billions of observations concentrated in less than 7% of the world’s surface and coding bias inadvertently leading to more ‘neo-colonialism’; data sovereignty; inclusion of local communities. All in all, this is an exciting field and I hope lots of people are working on it! Hopefully a few big players in AI would like to support conservation in this way too 🙏🙏🙏 Feel free to send me any interesting material or ideas on the topic for further research! Julien Herzen John Harper Daniele Silvestro Marc Oman Stephanie O'Donnell Wendy Elliott #naturetech GPAI (NOTE: yes, the image used was generated by AI; and no, AI was not used to generate any part of this post!)