SAVMAP

Near real-time ultrahigh-resolution imaging from unmanned aerial vehicles for sustainable land use management and biodiversity conservation in semi-arid savanna under regional and global change (SAVMAP) – project started on January 1st, 2014, funded by the Cooperation & development Center at EPFL (CODEV)

Abstract: To prevent aggravation of existing poverty in semi-arid savannas, a concept for the sustainable management and use of these ecosystems under unprecedented conditions is needed. SAVMAP is an innovative, inter-disciplinary initiative whose goal is to develop a monitoring tool for both sustainable land-use management and rare species conservation (black rhinoceros) in semi-arid savanna in Namibia. SAVMAP uses near real-time ultrahigh-resolution imaging (NURI) facilitated by unmanned aerial vehicles (UAVs) designed at EPFL.

Key-words: savanna, sustainable resource management, ultrahigh-resolution photographic imaging, conservation

 

The aim of the SAVMAP project is to use NURI from UAVs as a basis for developing an integrative monitoring tool for land managers, facilitating sustainable resource management and rare species conservation (black rhinoceros) in semi-arid savanna in Namibia. As far as we know, this is the first attempt to integrate an UAV-based remote sensing approach into a locally adapted land-use management strategy of semi-arid savanna. The specific objectives are to:

1.1) Acquire aerial images via use of UAVs and produce geo-referenced ultrahigh-resolution maps (< 10 cm resolution) of semi-arid savanna;

1.2) Acquire geo-referenced field data for ground-truthing (vegetation cover, animal identification, animal behaviour observation in response to UAV activity);

1.3) Perform in depth analysis of acquired data, and design image analysis workflows for quick and accurate land-cover and animal abundance determination. Compare output of UAV-based remote sensing to output of satellite-based remote sensing with respect to land-cover and animal abundance determination. Based on results from objectives a) and b) propose a land-management action plan for the local farmers.

1.4) Hold workshops and demonstrate the potential of UAVs in land-health and endangered species monitoring to local decision makers, government officials, farmers, game-guards, students, police officers, and scientists;

1.5) Hold courses to Namibian students studying resource management and nature conservation at the Polytech of Namibia (PoN) on the potential of UAVs in land-use management and conservation in savanna landscapes;

1.6) Train local scientists and land-managers to acquire necessary skills to take this project further.

 

Members of the SAVMAP Consortium

  • Dr. Friedrich F. Reinhard, Kuzikus Wildlife Reserve, Namibia, www.kuzikus.org [co-head]
  • Dr. Stéphane Joost, LASIG, EPFL, Lausanne, Switzerland, lasig.epfl.ch [co-head]
  • Prof Morgan Hauptfleisch, School of Natural Resources and Tourism, Polytechnic of Namibia, Windhoek, Namibia
  • Timothée Produit, LASIG, EPFL, Lausanne, Switzerland, lasig.epfl.ch
  • Matthew Parkan, LASIG, EPFL, Lausanne, Switzerland, lasig.epfl.ch
  • Sonja Betschart, Drone Adventure, Lausanne, Switzerland, droneadventures.org/
  • Adam Klaptocz, Drone Adventure, Lausanne, Switzerland, droneadventures.org/
  • Emanuele Lubrano, Drone Adventure, Lausanne, Switzerland, droneadventures.org/
  • Dr Patrick Meier, Qatar Computing Research Institute & iRevolution.net
  • Prof Devis Tuia, Laboratory of Geo-information Science and Remote Sensing, University of Wageningen, The Netherlands [since November 1st, 2017]

 

SAVMAP open dataset:

https://zenodo.org/record/1204408#.W2K8acJ9gck

 

SAVMAP papers:

– Ofli, F., Meier, P., Imran, M., Castillo, C., Tuia, D., Rey, N., Briant, J., Millet, P., Reinhard, F., Parkan, M., Joost, S., 2016. Combining Human Computing and Machine Learning to Make Sense of Big (Aerial) Data for Disaster Response. Big Data 4, 47–59. https://doi.org/10.1089/big.2014.0064

– Rey, N., Volpi, M., Joost, S., Tuia, D., 2017. Detecting animals in African Savanna with UAVs and the crowds. Remote Sensing of Environment 200, 341–351. https://doi.org/10.1016/j.rse.2017.08.026

– Kellenberger, B., Marcos, D., Tuia, D., 2018. Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning. Remote Sensing of Environment 216, 139–153. https://doi.org/10.1016/j.rse.2018.06.028

 

SAVMAP Master theses:

– Rey, N. 2016. Combining UAV-imagery and machine learning for wildlife conservation, MSc thesis, Section of Environmental Engineering (SIE), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne. [supervision: Joost, S. and Tuia, D.]

– Bacchilega, B. 2018. Land cover classification of the semi-arid Namibian savanna, MSc thesis, Section of Environmental Engineering (SIE), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne.[supervision: Joost, S. and Reinhard, F.]