ABSTRACT
Major humanitarian organizations face the crucial challenge of estimating land damage from conflict in developing countries. A lack of on the ground data collection motivates the use of satellite imagery to meet this challenge. However, existing analysis methods involving satellite imagery are time-consuming, require special expertise, or lack automation. To mitigate these obstacles, SatDash was designed using Sentinel-2 images and ACLED data to provide a classification of areas that have undergone land damage due to conflict in northwestern Nigeria and Mali. SatDash was constructed using free and publicly available images and is accompanied by a user-friendly dashboard that allows domain experts to train their own data and export it for future use.
The dashboard was created for a humanitarian organization, referred to as the DAAO, Damage Assessment and Aid Organization, and the design process adhered to four primary recommendations for a successful AI for Social Good (AI4SG) partnership that are further detailed in this paper. Within this paper, I draw attention to the context of CHI4Good research, detailing how the deployment phases of such systems often have their own set of potential barriers, along with describing ethical challenges that arise with this type of research. This paper focuses primarily on the design process and responses to both the constraints mentioned in literature and those presented by the DAAO. I acknowledge that AI applications, especially in development contexts, require close attention and context-specific awareness, and this is reflected through the conscious decision to include domain experts and ensure that the tool is only used for its intended purpose. When designing SatDash, the primary aim was to think critically about the involvement of local context and spur the conversation about inclusive design of similar systems in a large organization such as the DAAO. This research affirms that satellite imagery data can be used to assist humanitarian aid organizations with land change detection and demonstrates how human-in-the-loop systems can aid these organizations with identification of communities negatively impacted by hunger and recurring conflict.
- 2016. CHI 2016 Homepage. https://chi2016.acm.org/wp/Google Scholar
- Bright Aboh and Alphonse Mutabazi. 2020. Satellite Imagery Analysis for Land Use, Land Use Change and Forestry: A Pilot Study in Kigali, Rwanda. In Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies (Ecuador) (COMPASS ’20). Association for Computing Machinery, New York, NY, USA, 127–135. https://doi.org/10.1145/3378393.3402268Google ScholarDigital Library
- ACLED. 2020. ACLED. https://acleddata.com//dashboardGoogle Scholar
- ACLED. 2020. Code Book. https://acleddata.com/acleddatanew/wp-content/uploads/dlm_uploads/2019/04/ACLED_Codebook_2019FINAL_pbl.pdfGoogle Scholar
- Akiode Olukemi Adejoke, Oduyemi Kehinde Ok, and Yahaya Usman Badaru. 2014. Analysis of Change Detection of Birnin-Kudu Land Cover Using Image Classification And Vegetation Indices.Google Scholar
- Matthias Baumann and Tobias Kuemmerle. 2016. The impacts of warfare and armed conflict on land systems. Journal of Land Use Science 11, 6 (Aug 2016), 672–688. https://doi.org/10.1080/1747423x.2016.1241317Google ScholarCross Ref
- Matthias Baumann, Tobias Kuemmerle, Marine Elbakidze, Mutlu Ozdogan, Volker C. Radeloff, Nicholas S. Keuler, Alexander V. Prishchepov, Ivan Kruhlov, and Patrick Hostert. 2011. Patterns and drivers of post-socialist farmland abandonment in Western Ukraine. Land Use Policy 28, 3 (2011), 552–562. https://doi.org/10.1016/j.landusepol.2010.11.003Google ScholarCross Ref
- Xuehong Chen, Dedi Yang, Jin Chen, and Xin Cao. 2015. An improved automated land cover updating approach by integrating with downscaled NDVI time series data. Remote Sensing Letters 6 (01 2015), 29–38. https://doi.org/10.1080/2150704X.2014.998793Google Scholar
- Marshini Chetty and Rebecca Grinter. 2007. HCI4D. CHI ’07 extended abstracts on Human factors in computing systems - CHI ’07 (2007). https://doi.org/10.1145/1240866.1241002Google ScholarDigital Library
- Nick Couldry and Ulises A. Mejias. 2018. Data Colonialism: Rethinking Big Data’s Relation to the Contemporary Subject. Television & New Media 20, 4 (Feb 2018), 336–349. https://doi.org/10.1177/1527476418796632Google Scholar
- Earth Observing System. 2019. NDVI FAQ: All You Need to Know About NDVI. https://eos.com/blog/ndvi-faq-all-you-need-to-know-about-ndvi/Google Scholar
- Lina Eklund, Michael Degerald, Martin Brandt, Alexander V Prishchepov, and Petter Pilesjö. 2017. How conflict affects land use: Agricultural activity in areas seized by the Islamic State. Environmental Research Letters 12, 5 (2017), 054004. https://doi.org/10.1088/1748-9326/aa673aGoogle ScholarCross Ref
- EOS. 2019. Home. https://eos.com/blog/6-spectral-indexes-on-top-of-ndvi-to-make-your-vegetation-analysis-complete/Google Scholar
- Sheena Erete, Aarti Israni, and Tawanna Dillahunt. 2018. An intersectional approach to designing in the margins. Interactions 25, 3 (2018), 66–69. https://doi.org/10.1145/3194349Google ScholarDigital Library
- European Space Agency. 2020. Sentinel 2 Missions Online. https://sentinel.esa.int/web/sentinel/missions/sentinel-2Google Scholar
- Google Earth Engine. [n.d.]. Google Earth Engine Code Editor. https://code.earthengine.google.com/Google Scholar
- A.R Huete. 1988. A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment 25, 3 (1988), 295–309. https://doi.org/10.1016/0034-4257(88)90106-xGoogle ScholarCross Ref
- Human Rights Watch. 2019. World Report 2019: Rights Trends in Mali. https://www.hrw.org/world-report/2019/country-chapters/maliGoogle Scholar
- Human Rights Watch. 2020. “How Much More Blood Must Be Spilled?”. https://www.hrw.org/report/2020/02/11/how-much-more-blood-must-be-spilled/atrocities-against-civilians-central-maliGoogle Scholar
- Human Rights Watch. 2020. Mali: Militias, Armed Islamists, Ravage Central Mali. https://www.hrw.org/news/2020/02/10/mali-militias-armed-islamists-ravage-central-maliGoogle Scholar
- ICG. 2020. Violence in Nigeria’s North West: Rolling Back the Mayhem. https://www.crisisgroup.org/africa/west-africa/nigeria/288-violence-nigerias-north-west-rolling-back-mayhemGoogle Scholar
- Ahmed Iyanda. 2020. New report uncovers causes of farmer-herder conflict in Nigeria’s Northwest. http://venturesafrica.com/new-report-uncovers-causes-of-farmer-herder-conflict-in-nigerias-northwest/Google Scholar
- Hadi H. Jaafar and Eckart Woertz. 2016. Agriculture as a funding source of ISIS: A GIS and remote sensing analysis. Food Policy 64(2016), 14–25. https://doi.org/10.1016/j.foodpol.2016.09.002Google ScholarCross Ref
- Aditya Jain, Zerina Kapetanovic, Akshit Kumar, Vasuki Narasimha Swamy, Rohit Patil, Deepak Vasisht, Rahul Sharma, Manohar Swaminathan, Ranveer Chandra, Anirudh Badam, Gireeja Ranade, Sudipta Sinha, and Akshay Uttama Nambi S N. 2019. Low-Cost Aerial Imaging for Small Holder Farmers. In Proceedings of the 2nd ACM SIGCAS Conference on Computing and Sustainable Societies (Accra, Ghana) (COMPASS ’19). Association for Computing Machinery, New York, NY, USA, 41–51. https://doi.org/10.1145/3314344.3332485Google ScholarDigital Library
- Neal Jean, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, and Stefano Ermon. 2016. Combining satellite imagery and machine learning to predict poverty. Science 353, 6301 (2016), 790–794. https://doi.org/10.1126/science.aaf7894 arXiv:https://science.sciencemag.org/content/353/6301/790.full.pdfGoogle ScholarCross Ref
- Morten Jerven. 2013. Poor numbers: How we are misled by African development statistics and what to do about it. Cornell University Press.Google Scholar
- Y. J. Kaufman and D. Tanre. 1992. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS. IEEE Transactions on Geoscience and Remote Sensing 30, 2 (1992), 261–270.Google ScholarCross Ref
- Thomas M. Lillesand, Ralph W. Kiefer, and Jonathan W. Chipman. 2015. Remote sensing and image interpretation. John Wiley & Sons, Inc.Google Scholar
- D. Lu and Q. Weng. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing 28, 5 (2007), 823–870. https://doi.org/10.1080/01431160600746456Google ScholarDigital Library
- Susan K. Maxwell and Kenneth M. Sylvester. 2012. Identification of “ever-cropped” land (1984–2010) using Landsat annual maximum NDVI image composites: Southwestern Kansas case study. Remote Sensing of Environment 121 (2012), 186–195. https://doi.org/10.1016/j.rse.2012.01.022Google ScholarCross Ref
- Jiaxin Mi, Yongjun Yang, Shaoliang Zhang, Shi An, Huping Hou, Yifei Hua, and Fuyao Chen. 2019. Tracking the Land Use/Land Cover Change in an Area with Underground Mining and Reforestation via Continuous Landsat Classification. Remote Sensing 11, 14 (2019), 1719. https://doi.org/10.3390/rs11141719Google ScholarCross Ref
- Joyojeet Pal. 2017. CHI4Good or Good4CHI. Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA 17(2017). https://doi.org/10.1145/3027063.3052766Google ScholarDigital Library
- Caleb Robinson, Anthony Ortiz, Kolya Malkin, Blake Elias, Andi Peng, Dan Morris, Bistra Dilkina, and Nebojsa Jojic. 2020. Human-Machine Collaboration for Fast Land Cover Mapping. Proceedings of the AAAI Conference on Artificial Intelligence 34, 03(2020), 2509–2517. https://doi.org/10.1609/aaai.v34i03.5633Google ScholarCross Ref
- S. A. Sader and J. C. Winne. 1992. RGB-NDVI colour composites for visualizing forest change dynamics. International Journal of Remote Sensing 13, 16 (1992), 3055–3067. https://doi.org/10.1080/01431169208904102Google ScholarCross Ref
- Mehdi Sarparast. 2019. SAVI: Soil-Adjusted Vegetation Index in LSRS: Land Surface Remote Sensing. https://rdrr.io/cran/LSRS/man/SAVI.htmlGoogle Scholar
- Jan Niklas Schmid. 2017. Using Google Earth Engine for Landsat NDVI time series analysis to indicate the present status of forest stands. Ph.D. Dissertation. https://doi.org/10.13140/RG.2.2.34134.14402/6Google Scholar
- Umar Serajuddin, Hiroki Uematsu, Christina Wieser, Nobuo Yoshida, and Andrew Dabalen. 2015. Data Deprivation: Another Deprivation to End. Policy Research Working Papers(2015). https://doi.org/10.1596/1813-9450-7252Google Scholar
- Yashwant Singh. [n.d.]. Significance Of Land Use / Land Cover (LULC) Maps. https://www.satpalda.com/blogs/significance-of-land-use-land-cover-lulc-mapsGoogle Scholar
- William L Stefanov, Michael S Ramsey, and Philip R Christensen. 2001. Monitoring urban land cover change: An expert system approach to land cover classification of semiarid to arid urban centers. Remote Sensing of Environment 77, 2 (2001), 173–185. https://doi.org/10.1016/s0034-4257(01)00204-8Google ScholarCross Ref
- Kara Stevens, Lindsay Campbell, Gerald Urquhart, Dan Kramer, and Jiaguo Qi. 2011. Examining complexities of forest cover change during armed conflict on Nicaragua’s Atlantic Coast. Biodiversity and Conservation 20, 12 (May 2011), 2597–2613. https://doi.org/10.1007/s10531-011-0093-1Google ScholarCross Ref
- Qiuhong Tang and Taikan Oki. 2007. Daily NDVI Relationship to Cloud Cover. Journal of Applied Meteorology and Climatology 46, 3 (Jan 2007), 377–387. https://doi.org/10.1175/jam2468.1Google ScholarCross Ref
- Prasad S. Thenkabail, Eden A. Enclona, Mark S. Ashton, and Bauke Van Der Meer. 2004. Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications. Remote Sensing of Environment 91, 3-4 (2004), 354–376. https://doi.org/10.1016/j.rse.2004.03.013Google ScholarCross Ref
- Nyein Soe Thwal, Takaaki Ishikawa, and Hiroshi Watanabe. 2019. Land cover classification and change detection analysis of multispectral satellite images using machine learning. In Image and Signal Processing for Remote Sensing XXV, Lorenzo Bruzzone and Francesca Bovolo (Eds.), Vol. 11155. International Society for Optics and Photonics, SPIE, 522 – 532. https://doi.org/10.1117/12.2532988Google Scholar
- Nenad Tomašev, Julien Cornebise, Frank Hutter, Shakir Mohamed, Angela Picciariello, Bec Connelly, Danielle C. M. Belgrave, Daphne Ezer, Fanny Cachat Van Der Haert, Frank Mugisha, and et al.2020. AI for social good: Unlocking the opportunity for positive impact. Nature Communications 11, 1 (2020). https://doi.org/10.1038/s41467-020-15871-zGoogle Scholar
- Giovanna Trianni, Emanuele Angiuli, Gianni Lisini, and Paolo Gamba. 2014. Human settlements from Landsat data using Google Earth Engine. 2014 IEEE Geoscience and Remote Sensing Symposium (2014). https://doi.org/10.1109/igarss.2014.6946715Google ScholarCross Ref
- UNHCR. 2019. Nigeria emergency. https://www.unhcr.org/en-us/nigeria-emergency.htmlGoogle Scholar
- M. Usman, R. Liedl, M. A. Shahid, and A. Abbas. 2015. Land use/land cover classification and its change detection using multi-temporal MODIS NDVI data. Journal of Geographical Sciences 25, 12 (Jun 2015), 1479–1506. https://doi.org/10.1007/s11442-015-1247-yGoogle ScholarCross Ref
- World Food Programme. 2020. Situation Report - Nigeria, March 31, 2020. https://www.wfp.org/publications/NigeriaGoogle Scholar
- World Food Programme. 2020. WFP Mali Country Brief, April 2020 - Mali. https://reliefweb.int/report/mali/wfp-mali-country-brief-april-2020Google Scholar
- Jinru Xue and Baofeng Su. 2017. Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications. Journal of Sensors 2017(2017), 1–17. https://doi.org/10.1155/2017/1353691Google ScholarCross Ref
- Ellen Zegura, Carl DiSalvo, and Amanda Meng. 2018. Care and the Practice of Data Science for Social Good. In Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies (Menlo Park and San Jose, CA, USA) (COMPASS ’18). Association for Computing Machinery, New York, NY, USA, Article 34, 9 pages. https://doi.org/10.1145/3209811.3209877Google ScholarDigital Library
- Chunfang Zhou and Aparna Purushothaman. 2018. Developing Creativity and Learning Design by Information and Communication Technology (ICT) in Developing Contexts. Encyclopedia of Information Science and Technology, Fourth Edition (2018), 4178–4188. https://doi.org/10.4018/978-1-5225-2255-3.ch362Google Scholar
Recommendations
Hyperspectral indices for assessing damage by the solenopsis mealybug (Hemiptera: Pseudococcidae) in cotton
Phenacoccus solenopsis Tinsley, a native of North America, is a widespread exotic mealybug infesting cotton, Gossypium spp. in several countries. Monitoring of this pest is generally undertaken through regular field surveys, which is labour intensive, ...
Geospatial Analysis of Land Loss, Land Cover Change, and Landuse Patterns of Kutubdia Island, Bangladesh
This study utilizes geospatial tools of remote sensing, geographical information systems GIS, and global positioning system GPS to examine the land loss, land cover LC change, landuse of Kutubdia Island, Bangladesh. Multi-spectral Scanner MSS, Thematic ...
Land Conversion from Marsh Into Cropland in the Sanjiang Plain During the Past 30 Years
KAM '11: Proceedings of the 2011 Fourth International Symposium on Knowledge Acquisition and ModelingTo discover the process and rules of regional land conversion from marsh into cropland, based on remote sensing and GIS technology, this paper integrated topographic maps and remotely sensed data, and analyzed the process and driving forces of land ...
Comments