From 6b03d8166b39fbab4825ae4b950513c5cfe51084 Mon Sep 17 00:00:00 2001 From: "claudio.delosreyes@hotosm.org" Date: Tue, 7 Jan 2025 11:52:06 -0500 Subject: [PATCH] Added Filling Osm Buildings Data Gaps In Lebanon --- ...sm-buildings-data-gaps-in-lebanon.markdown | 56 +++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 _drafts/filling-osm-buildings-data-gaps-in-lebanon.markdown diff --git a/_drafts/filling-osm-buildings-data-gaps-in-lebanon.markdown b/_drafts/filling-osm-buildings-data-gaps-in-lebanon.markdown new file mode 100644 index 0000000000..f47841c155 --- /dev/null +++ b/_drafts/filling-osm-buildings-data-gaps-in-lebanon.markdown @@ -0,0 +1,56 @@ +--- +title: Filling OSM buildings data gaps in Lebanon +date: 2025-01-07 15:53:00 Z +Summary Text: "Following conflict escalation from October 2023 to November 2024, a + ceasefire deal was reached between relevant actors on 27 November, 2024. As the + country begins to recover from the months of war, information is needed on the extent + of the damage to inform humanitarian programming. Economic impact, service disruption, + and general shelter needs all need accurate damage estimates. A key factor of estimating + damage from the conflict is the location of buildings, before any were damaged, + pre-conflict. \n\n### Data gaps\n\nBased on requests from humanitarian analysts + needing accurate building footprints for precise damage analyses, HOT did an initial + assessment of OpenSteetMap and Microsoft Machine Learning buildings. We found that + these go-to data sources for open data lacked the accuracy needed for reliable damage + assessments. \n\n**Microsoft ML**: A visual analysis of [Microsoft Machine Learning](https://github.com/microsoft/GlobalMLBuildingFootprints) + (ML) buildings identified poor precision, as shown in blue below. Some buildings + are missed, and in some cases, multiple buildings are grouped together. \n\n![](AD_4nXcINdQeaP3lgB_2hxtSPM1LN-CZ8FxZkyyoYD3GL4JM0i9_FzswcDwHLgp__KP09Vo9S_GHrb4W4D2n-G3kdPNrFI1lhURf_r58pO7kN4tEuphb6r5RrnIadS7-qj0RbZbTPdHbHg.png)\n**OSM**: + OpenStreetMap buildings had major coverage gaps in Lebanon, as identified by the + absence of any OSM buildings in the area shown above and data gaps in the map below.  \n\n![](AD_4nXc6P4WKDiQoumiDHPoOL4sObR53SUCSQSHLo8CfxPeRY_pHq8oLZp_wQlLga91jz2v_eoXlznTTtTbwOzVxsn0kFfp1fyz15z_p_8ptEk3_VlpaGYLWlOmu2AQq8oj-oT-sgyxS.png)\n\n**Filling + buildings data gap in OSM**  \n \nAs a precise pre-conflict building footprints + dataset did not exist and is needed to refine locations of damage detected remotely + through satellite, HOT kicked off a project in October 2024 with global volunteers + and a growing OSM community in Lebanon to crowdsource mapping pre-conflict building + footprints.  \n\nBy the end of December 2024, over 100 volunteers have contributed + over 150,000 edits! We anticipate completion of the 3 southern states of Sour, Bent + Jbeil, and Marjayoun by early February, 2025. We will then review priority areas, + but anticipate mapping Jezzine, Saida, El Nabatieh, Hasbaya, and southern Beirut. + We’ve been prioritizing areas based on humanitarian requests, and initial damage + estimates. You can track the progress of areas mapped and validated in this [map](https://umap.openstreetmap.fr/en/map/lebanon-conflict-2024-tasking-manager-project-prog_1132719#10/33.3758/35.2359) + (screenshot below as of 6 Jan ‘25), and learn more [here](https://wiki.openstreetmap.org/wiki/Lebanon:_Conflict_-_October_2024). \n![](AD_4nXc9s7n5Um1Hi4LNTsVBWPLcVh6pU3ypSt--c3X88JeAI5HxYZdaVB_wrf8GeE3yN5S1XRjPKQt2sksB-a_Uzt-lWisIgNZoSfvZCAcY2_IShXJLTtiB9UX_RUiNsmDU2yHoSRXw.png)\n\n**Example + early data improvements in OSM** \n\nThe first district completed in the update + was Marjayoun southeast Lebanon. The data improvement is evident by the increase + in OSM of total count of buildings and compared to Microsoft ML building counts + in all of Marjayoun District: ![](AD_4nXcoBLGYsDd-1pcsSIph_M1LuCoS6ANaffXVofQqzSTT_Z4GatQc_wsbBn7toKP2Fn3IVsBqhnUOQOR-qHkszysF6LVU4SU3d3so9QcLKdqIAGMLur27utg6ycwGYc2Em-dLVmwrOg.png)\n\n![](AD_4nXekvxvN42bVYOtLbL90EKLV4pzbtysJKoq7BdQ8YDCgJH89PnAkdqG5XxhY1z4HApO5y4rVIlA0P4en78EZXMlHkI75FDt_-1pqGLSxkCjSzx2UjN8Ze46qw-OHJIL6aJNjMfePSQ.png)\n\n\n**Next + steps & identifying damaged buildings** \n\n**Data access**: All map edits are live + in OSM. You can access the most updated OSM data through [HOT’s export tool](http://export.hotosm.org/)or + [HDX](https://data.humdata.org/dataset/hotosm_lbn_buildings).\n\n**Analysing damage**: + Building footprints are commonly used as a data input in remote damage analyses. + With support from the [H2H Network](https://h2hnetwork.org/h2hsupport-package-conflict-lebanon/)’s + Lebanon Activation, HOT is working to better understand how OSM buildings are used + by partner-led damage analyses. Remote damage analyses differ depending on the leading + organization and method (eg UNOSAT and the Decentralized Damage Mapping Group). + HOT plans to create an overview of different remote damage detection methods to + serve as a data-usage guide. The overview will contain information on the data inputs + (including OSM), and how the information contained in each output can be used by + humanitarians. \n\n**How to get involved**\n\n**Mapping**: If you are interested + in mapping (digitizing) buildings in Lebanon, check out HOT’s [Tasking Manager](https://tasks.hotosm.org/) + and look for projects in Lebanon! \n\n**Damage analyses**: If you are a humanitarian + data analyst conducting or using damage assessments or OSM data in Lebanon, we’d + love to hear from you about your experience at[data@hotosm.org](mailto:data@hotosm.org). + We’d also appreciate any input on priority areas to map next. \n\n****All of HOT’s + work in conflict is in line with [HOT’s Data Principles](https://www.hotosm.org/tools-and-data/data-principles/). + See our [Program on Conflict & Displacement](https://www.hotosm.org/programs/conflict-displacement) + for more information.*** " +--- + +Recent conflict has impacted the humanitarian situation in Lebanon. With damaged buildings estimated at up to 25% near the southern border, accurate data is needed to plan a humanitarian response. HOT is working with volunteers to crowdsource the mapping of pre-conflict buildings footprints to serve as a baseline dataset and improve the accuracy of damage estimates. \ No newline at end of file