10 November 2019
| Dataset date: January 01, 2016-October 29, 2016
1) Natural disaster events include avalanches,earthquake, flooding, heavy rainfall & snowfall, and landslides & mudflows as recorded by OCHA field offices and IOM Afghanistan Humanitarian Assistance Database (HADB).
2) A natural disaster incident is defined as an event that has affected (i.e. impacted) people, who may or may not require humanitarian assistance.
3) HADB information is used as a main reference and supplemented by OCHA Field Office reports for those incidents where information is not available from the HADB. OCHA information includes assessment figures from OCHA, ANDMA, Red Crescent Societies, national NGOs, international NGOs, and ERM.
4) The number of affected people and houses damaged or destroyed are based on the reports received. These figures may change as updates are received.
10 November 2019
| Dataset date: January 01, 2014-December 31, 2014
1) Natural disaster events include avalanches, extreme winter conditions, flooding, heavy rainfall, landslides & mudflows, and extreme weather (sandstorms, hail, wind, etc) as recorded by OCHA field offices and IOM Afghanistan Humanitarian Assistance Database (HADB). 2) A natural disaster incident is defined as an event that has affected (i.e. impacted) Afghans, who may or may not require humanitarian assistance. 3) HADB information is used as a main reference and supplemented by OCHA Field Office reports for those incidents where information is not available from the HADB. OCHA information includes assessment figures from OCHA, ANDMA, Red Crescent Societies, national NGOs, international NGOs, and ERM.
10 November 2019
| Dataset date: August 31, 2016-August 31, 2016
On the 26th of October 2015, a large scale earthquake caused shelter damage throughout much of northern and central Afghanistan. During August 2016, the REACH Initiative (supported by ACTED, AfghanAid and People in Need) conducted a shelter response evaluation in 3 districts of Afghanistan on behalf of the Shelter Cluster. The aim of the assessment was to evaluate shelter interventions and locate possible intervention gaps in order to inform the shelter cluster of Afghanistan of the current shelter context and needs of earthquake affected families. The assessment consisted of three specific areas of investigation:
1. To monitor change in sheltering conditions for families
2. To evaluate the value of various shelter interventions in allowing families to recover and to identify possible gaps
3. To determine recovery limitations and successes relating to vulnerable groups
9 April 2019
| Dataset date: October 10, 2018-October 20, 2018
About the dataset:
Hurricane Michael was the third-most intense Atlantic hurricane to make landfall in the United States in terms of pressure. This dataset was collected from Twitter during Hurricane Michael. The dataset was processed and analyzed using the AIDR (http://aidr.qcri.org) platform.
This is a Twitter dataset collected during Hurricane Michael 2018. The data was collected, processed, and analyzed by the AIDR (http://aidr.qcri.org) platform using state-of-the-art machine learning techniques. The data includes the number of injured and dead people, infrastructure damage reports, missing or found people, urgent needs and donation offers for each hour. Due to Twitter TOS, we do not share full tweets content on HDX. Please contact us via HDX or on email@example.com to get tweet ids of the dataset along with a tool which can be used to rehydrate tweets from tweet ids.
4 November 2018
| Dataset date: September 20, 2017-October 03, 2017
This resource is comprised of Twitter data collected and processed by the AIDR system during the 2017 hurricane Maria. The data contains information about number of people affected, injured, dead, reports of damages, missing people and so on. Please contact us if you need full dataset with tweets content.
9 August 2018
| Dataset date: December 26, 2016-December 26, 2016
This dataset contains:
windspeeds of Typhoon Nina
rainfall of Typhoon Nina
Priority Index of Typhoon Nina
The predicted priority index of Typhoon Nina is produced by a machine learning algorithm that was trained on five past typhoons: Haiyan, Melor, Hagupit and Rammasun and Haima, It uses base line data for the whole country, combined with impact data of windspeeds and rains, and trained on counts by the Philippine government on houses damaged and completely destroyed.
The output is a weighted index between partially damaged and completely damaged, where partially damaged is counted as 25% of the completely damaged. This has proven to give he highest accuracy.
The absolute number of houses damaged / people affected is insufficiently validated at the moment, and should just be used for further trainng and ground-truthing.
The model has an best r2 score of 0.794933727 and an accuracy of 0.699470899
Administrative boundaries (P_Codes) - Philippines Government; Published by GADM and UN OCHA (HDX)
Census 2015 (population) - Philippine Statistics Authority; received from UN OCHA (HDX)
Avg. wind speed (mph) - University College London
Typhoon path - University College London
Houses damaged - NDRRMC
Rainfall - GPM
Poverty - Pantawid pamilyang pilipino program (aggregated)
Roof and wall materials
New geographical features
All the columns with feat_ indicates the importance of that feature, if not present that feature was not used.
learn_matrix name of the learning matrix with the 5 typhoons
run_name unique run name (pickle files and csv files have this name for this model)
typhoon_to_predict name of a new typhoon to predict
val_accuracy accuracy based on 10 categories of damage 0% 10% 20% …
val_perc_down perc of underpredicted categories
val_perc_up perc of overpredicted categories
Val_best_score best r2 score
Val_stdev_best_score error on best score based on the CV
Val_score_test r2 score on the test set (this should be around +- 5% of the previus number to not overfit
Val_mean_error_num_houses average error on the number of houses
val_std_error_num_houses std deviation of the errors (lower is better)
Algorithm developed by 510.global the data innovation initiative of the Netherlands Red Cross.
27 December 2016
| Dataset date: December 19, 2016-December 19, 2016
This map illustrates the percentage of buildings damaged in the city of Aleppo, Syrian Arabic Republic, as determined by satellite imagery analysis. Using satellite imagery acquired 18 September 2016, 01 May 2015, 26 April 2015, 23 May 2014, 23 September 2013, and 21 November 2010, UNOSAT identified a total of 33,521 damaged structures within the extent of this map. These damaged structures are compared with total numbers of buildings found in a pre-conflict satellite image collected in 2009 to determine the percentage of damaged buildings across the city. Based on this analysis and in the map extent, in 19 neighborhoods the number of damaged buildings is more than 40%. The most damaged is Al Aqabeh with 65.61% of buildings damaged and the most significant change since UNOSAT’s 2015 analysis is Khalidiyeh, which increased in percentage damage from 4.20% to 55.80%. Note that this analysis considers only damage in residential areas and excludes industrial areas. This is a preliminary analysis and has not yet been validated in the field. Please send ground feedback to UNITAR - UNOSAT.