Remote sensing and social sensing for flood mapping
Remote sensing and social sensing for flood mapping is provided by identifying where floodwater is present in an image of a location affected by a flooding event; identifying a social media post posted on a social media platform from the location and associated with the flooding event; and overlaying the image with the social media post. In some embodiments, the remote and social sensing includes one or more of: generating a permanent water mask identifying where permanent water is located at the location, and applying the permanent water mask to the image to differentiate the floodwater from permanent water for the location; identifying where the social media post was posted from; and overlaying the image with the social media post includes positioning a photograph included in the social media post for display with the image where a subject of the photograph is located at the location.
1 . A method, comprising:
identifying where floodwater is present in a current image of a location affected by a flooding event, wherein identifying where floodwater is present in the current image of the location affected by the flooding event comprises:
generating a permanent water mask identifying where permanent water is located at the location; and
applying the permanent water mask to the current image to generate a differentiated image that separately indicates the floodwater from permanent water for the location;
identifying a social media post posted on a social media platform from the location and associated with the flooding event; and
overlaying the differentiated image over the social media post, wherein the social media post includes a photograph of the location, wherein overlaying the differentiated image over the social media post includes positioning the photograph for display with the differentiated image where a subject of the photograph is located at the location.
2 . The method of claim 1 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises identifying where the social media post was posted from based on at least one of:
geolocation information included with the social media post; and
a geolocation inference based on user location data, user profile description data, and text included in the social media post.
3 . The method of claim 1 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises filtering the social media platform for relevant social media posts, including the social media post, based on keywords and time data included in a corpus of social media posts including the relevant social media posts.
4 . The method of claim 1 , wherein social media posts from a social media service are filtered to identify the social media post by removing any social media posts that fall below or outside of any of:
a disaster type threshold;
an informativeness threshold;
a humanitarian threshold; and
a geographic threshold.
5 . The method of claim 4 , wherein the social media posts are filtered to remove duplicates and follow-on social media posts to original social media posts that do not also conform to the informativeness threshold.
6 . A system, comprising:
a processor; and
a memory, including instructions that when executed by the processor perform operations comprising:
identifying where floodwater is present in a current image of a location affected by a flooding event, wherein identifying where floodwater is present in the current image of the location affected by the flooding event comprises:
generating a permanent water mask identifying where permanent water is located at the location; and
applying the permanent water mask to the current image to generate a differentiated image that separately indicates the floodwater from permanent water for the location;
identifying a social media post posted on a social media platform from the location and associated with the flooding event; and
overlaying the differentiated image over the social media post, wherein the social media post includes a photograph of the location, wherein overlaying the differentiated image over the social media post includes positioning the photograph for display with the differentiated image where a subject of the photograph is located at the location.
7 . The system of claim 6 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises identifying where the social media post was posted from based on at least one of:
geolocation information included with the social media post; and
a geolocation inference based on user location data, user profile description data, and text included in the social media post.
8 . The system of claim 6 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises filtering the social media platform for relevant social media posts, including the social media post, based on keywords and time data included in a corpus of social media posts including the relevant social media posts.
9 . The system of claim 6 , wherein social media posts from a social media service are filtered to identify the social media post by removing any social media posts that fall below or outside of any of:
a disaster type threshold;
an informativeness threshold;
a humanitarian threshold; and
a geographic threshold.
10 . The system of claim 9 , wherein the social media posts are filtered to remove duplicates and follow-on social media posts to original social media posts that do not also conform to the informativeness threshold.
11 . A memory including instructions that when executed by a processor perform operations comprising:
identifying where floodwater is present in a current image of a location affected by a flooding event, wherein identifying where floodwater is present in the current image of the location affected by the flooding event comprises:
generating a permanent water mask identifying where permanent water is located at the location; and
applying the permanent water mask to the current image to generate a differentiated image that separately indicates the floodwater from permanent water for the location;
identifying a social media post posted on a social media platform from the location and associated with the flooding event; and
overlaying the differentiated image over the social media post, wherein the social media post includes a photograph of the location, wherein overlaying the differentiated image over the social media post includes positioning the photograph for display with the differentiated image where a subject of the photograph is located at the location.
12 . The memory of claim 11 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises identifying where the social media post was posted from based on at least one of:
geolocation information included with the social media post; and
a geolocation inference based on user location data, user profile description data, and text included in the social media post.
13 . The memory of claim 11 , wherein identifying the social media post posted on the social media platform from the location and associated with the flooding event further comprises filtering the social media platform for relevant social media posts, including the social media post, based on keywords and time data included in a corpus of social media posts including the relevant social media posts.
14 . The memory of claim 11 , wherein social media posts from a social media service are filtered to identify the social media post by removing any social media posts that fall below or outside of any of:
a disaster type threshold;
an informativeness threshold;
a humanitarian threshold; and
a geographic threshold.