Andy Jarvis Parasid Near Real Time Monitoring Of Habitat Change Using A Neural Netwrok And Modis Data Conida Sept 2009
Download as PPT, PDF0 likes1,452 views
The document outlines the PARASID approach for near-real-time monitoring of habitat change using neural networks and MODIS data, focusing on detecting human impacts on ecosystems through NDVI analysis. It details the methodology involving machine learning techniques, including Bayesian neural networks, to predict and analyze vegetation changes across Latin America. Initial results indicate a significant increase in deforestation rates, and the system aims to provide comprehensive global monitoring by 2011.
Andy Jarvis Parasid Near Real Time Monitoring Of Habitat Change Using A Neural Netwrok And Modis Data Conida Sept 2009
- 1. Near-real time monitoring of habitat change using a neural network and MODIS data: the PARASID approach Andy Jarvis, Louis Reymondin, Jerry Touval
- 2. Contents The approach The implementation Some examples Comparison with other models Plans and timelines
- 3. Objectives of PARASID HUman Impact Monitoring And Natural Ecosystems Provide near-real time monitoring of habitat change (<3 month turn-around) Continental – global coverage (forests AND non-forests) Regularity in updates
- 4. The Approach The change in greenness of a given pixel is a function of: Climate Site (vegetation, soil, geology) Human impact
- 5. Machine learning We therefore try to learn how each pixel (site) responds to climate, and any anomoly corresponds to human impact Machine learning (or neural-network), is a bio-inspired technology which emulates the basic mechanism of a brain. It allows To find a pattern in noisy dataset To apply these patterns to new dataset
- 6. NDVI Evolution and novelty detection Novelty/Anomoly
- 7. NDVI Cleaning using HANTS Eliminate all short-term variations Uses NDVI quality information Iterative fitting of cleaned curve using Fourier analysis Least-square fitting to good quality values
- 8. Methodology As required by the ARD algorithm, each input and the hidden output is a weights class with its own α α 0 α c INPUTS : Past NDVI (MODIS 3b42) Previous rainfall (TRMM) Temperature (WorldClim) OUTPUT : 16 day predicted NDVI NDVI t Precipitation (t) Temperature (t) … … w 0 w 1 w 2 NDVI (t-1) NDVI (t-2) NDVI (t-n) w p1 w p2 w p3 w o1 w o2 w o3
- 9. Methodology – Bayesian NN To detect novelties, Bayesian Neural Networks provide us two indicators The predicted value The probability repartition of where the value should be The first one allows us to detect abnormal measurements The second one allows us to say how sure we are a measurement is abnormal.
- 10. The Processing For South America alone, first calculations approximated 10 years of processing for the NN to learn: A map of 30720 by 37440 pixels 1,150,156,800 vectors 23 vectors per year 26,453,606,400 NDVI values to manage per year 9.5 years of data 251,309,260,800 individual data points Through various processes, optimizations and hardware acquisitions reduced time to 3 months for NN learning Detection takes 2-3 days
- 12. The Bottom-Line 250m resolution Latin American coverage (currently) 3 week turnaround from data being made available (4 week delay in MODIS going to NASA ftp) (3+4 = 7 weeks) Report every 16 days Measurement of scale of habitat change (0-1) and probability of event
- 13. An Example - Caquetá Training From 2000 to end of 2003 Detections From 2004 to May of 2009
- 14. Detection results for Caquetá – Meta Analysis 25 May 2009 1.0 0.0 Novelty probabilities
- 15. Detection : See Caqueta-meta KML See http://www.youtube.com/watch?v=exGmzc70PrQ Pink : Too many clouds to analyse Red : 3 consecutive times detected with more than 95% confidence
- 16. Deforestation Rates on the Rise
- 17. Some statistics 75% of deforestation occurs in December and January 50,000 Ha deforested in Dec/Jan of 2008/2009 compared with 7,500 Ha in 2004/2005 During 16 days of Christmas in 2008 16,000 Ha lost, compared with 500 Ha in 2004 (3%)
- 19. Other Examples
- 20. Chile
- 21. Bolivia
- 22. Paraguay
- 23. Argentina
- 24. OTCA
- 25. Model comparison PARASID vs. FORMA PARASID detections First detection in 2004 FORMA probabilities First detection in 2000
- 26. PARASID vs DETER It seems Parasid model detects quite small and isolate events which Deter doesn’t detect. 2006 2004
- 27. Next Steps Fully functioning web interface January 2010 Continental validation and calibration (January 2010) Global extent (2011) Additional models to identify type of change (drivers) (2011)
- 28. Analysis of three images between the years 2000 and 2009. MATO-GROSSO – BRASIL LAT: - 10.1, LON: - 51.3 10/10/2000 LANDSAT 7 SLC ON 29/06/2009 LANDSAT 7 SLC OFF CLASSIFIED IMAGES IN ERDAS Forest Uncoverage Change 00-09 Unchanged CHANGE DETECTION IN ERDAS
- 29. SAMPLING POINTS IN LATIN-AMERICA 1. Covering the whole Latin-America 2. Sampling of different land use type Tropical forest Andes Savanna Desert 3. Selection of areas with high risk of change Near to cities Near to road Near to rivers With crops already existing SELECTION CRITERIA
- 30. Conclusions Near-real time global monitoring is possible PARASID now functioning for Latin America Providing first approximations of deforestation rates in over a decade for some parts of Latin America
- 31. GRACIAS!