Improving Forest Loss Mapping In Nepal Using Landtrendr Time-Series And Machine Learning
--
https://doi.org/10.1016/j.rsase.2025.101864 <-- share paper
--
“HIGHLIGHTS:
• ViT-based forest mask, multispectral ensemble LandTrendr and terrain shadow mask.
• District-level RF/XGBoost model training with expert-weighted validation.
• Outperformed GFC and REDD + AI benchmarks in accuracy and F1 performance.
• RF excelled in High Mountains/Himalayas; XGBoost in the lower Mountain regions.
• NBR contributed the most; snow-impacted forest loss uncertainty was observed..."
#Forestdisturbance #forest #disturbance #remotesensing #LandTrendr #workflow #timeseries #ViT #RF #XGBoost #GEE #Nepal #ForestNepal #spatial #GIS #mapping #earthobservation #landsat #Himalayas #mountains #alpine #vegetation #AI #multispectral #monitoring #spatialanalysis #spatiotemporal #loss #change #machinelearning #NDR #conservation #planning #policy #mitagion #ecology #Karnali #Bagmati, #Darchula #Siwalik #GlobalForestChange #Degradation
Cameras that see the unseen promise smarter, faster recycling of everyday waste

A new study uses advanced imaging technology to identify materials in municipal solid waste that can be separated for recycling or to produce energy.

Tech Xplore
Am vergangenen Freitag und Samstag fand unser Sommerkurs „Schriftkulturen des Mittelalters in digitaler Perspektive“ in der Staatsbibliothek zu Berlin statt (https://blog.sbb.berlin/termin/mittelalterliche-schriftkulturen-in-digitaler-perspektive/). Neben #TEI und #HTR ging es auch um #multispectral imaging und Materialanalyse. Wir hatten tolle Teilnehmende, die in den verschiedenen Hands-On-Sessions mitgemacht haben, z.b. in unserem Handschriftenlesesaal, um das digitale DinoLite-Mikroskop (UV, VIS, IR) kennenzulernen.
Monday is the start of the summer school in #digital #palaeography which I run in Göttingen every summer. We have 16 amazing international students and 2 weeks to play with #medieval fragments, #multispectral imaging, network analysis, bookbindings, biocodicology and much much more, topped off by a trip to the fabulous @hab_wf and a hackathon. It's the absolute highlight of my year. Follow this year's posts and photos via #SummerSchool25. @histodons @medievodons @historikerinnen
Over the past week, we've conducted drone surveys at archaeological sites in Sinarcas, Caudete de las Fuentes, Ademuz, and Moixent, using #multispectral and #LiDAR sensors. A big thank you to the #NTNU University Museum for their invaluable support, particularly to Professor Ole Risbøl and Magnar Mojaren Gran for their expertise. Through this collaboration, we’ve had the opportunity to learn from their extensive knowledge, enhancing our skills and understanding while working with these methods.
[New Video] Real-time Human Detection with 4-Band Raspberry Pi Camera
Check out our new demo video showing real-time human detection using a 4-Band Raspberry Pi Camera! The video displays the camera's view along with inference results highlighting detected humans.
🎥 Demo Video: https://youtu.be/oafrmEUXJYA?si=mPRbKomyCWjVvOAb
📄 Paper: https://doi.org/10.3390/jimaging11040093
#Multispectral #ComputerVision #EdgeAI #RaspberryPi #HumanDetection
Real-time Human Detection with 4-Band Raspberry Pi Camera

YouTube
[New Paper] A Color‑Based Multispectral Imaging Approach for a Human‑Detection Camera
“HitoMi‑Cam” uses a 4‑band snapshot filter + Raspberry Pi to detect humans in real‑time (15 fps).
📄 Paper: https://doi.org/10.3390/jimaging11040093
🎥 Demo: https://youtu.be/VE2gudrNOCs?si=HBEnEruAqIxxN1Dt
#Multispectral #ComputerVision #EdgeAI
The Harmonized Landsat Sentinel-2 Project Releases Vegetation Indices | NASA Earthdata

This is a news item about the suite of vegetation indices released by the HLS project.

NASA Earthdata
A Google-backed weapon to battle wildfires made it into orbit | TechCrunch

The constellation will keep a close eye on wildfires, eventually imaging nearly all of the Earth’s surface once every 20 minutes.

TechCrunch