To create Kuwait Finder initially back in 2012, a five-person staff at Kuwait\u2019s Public Authority for Civil Information (PACI) tapped into the country\u2019s long-term investment in geographic information system (GIS) technology. The GIS team pulled together data from various ministries, as well as PACI\u2019s internal paper maps and AutoCAD files, to capture the current basemap. With the objective of updating the construction of new buildings and changes to the city\u2019s streets, they studied satellite imagery to extract details for the map. But by the time the crew found the changes and input them back into the Kuwait Finder database, the infrastructure of Kuwait City had changed once again.<\/p>\r\n
\u201cWhere are the new streets? Where are the building footprints?\u201d Maher Abdel Karim, PACI\u2019s GIS consultant said recently, summarizing the challenges. \u201cOnce we were finished updating them, there would be new satellite imagery we\u2019d missed, and we\u2019d have to repeat the process again.\u201d<\/p>\r\n
<\/p>\r\n
![\"\"](\"https:\/\/www.esrith.com\/wp-content\/uploads\/2021\/11\/Kuwait_OldNew_826-768x432-539x303.jpg\")
<\/p>\r\n
<\/p>\r\n
PACI needed to make necessary changes to Kuwait Finder in a way that was quick, inexpensive, accurate and simple\u2014the more automated, the better. Compared to the vast resources available to a company like Google, PACI\u2019s size and budget were limited.<\/p>\r\n
PACI researched the viability of artificial intelligence to provide a solution. \u201cWe thought, how can we use AI to automate the process?\u201d Abdel Karim said. \u201cWe wanted to use machine learning to extract street data and building footprints from the satellite imagery while using the minimum amount of human input.\u201d<\/p>\r\n
<\/p>\r\n
Deep Learning to the Rescue<\/strong><\/p>\r\n Deep learning, a powerful form of AI, involves teaching a computer to detect patterns in large amounts of data, and to recognize and extract just the information you want. If done right, the algorithm acts quickly and thoroughly and even finds changes that human intuition would miss.<\/p>\r\n PACI\u2019s GIS team needed to teach the computer how to recognize building footprints from satellite data, and also note which ones were new since the last batch of satellite images. Elsewhere in the Middle East, an oil-and-gas company used machine learning to alert it if any new structures were being built near its thousands of miles of pipeline. PACI\u2019s task was a bit more complex as it wanted the computer to tell it about anything new across the entire country.<\/p>\r\n <\/p>\r\n <\/p>\r\n If properly trained, a machine learning algorithm can move conceptual mountains. At the beginning of the process, however, the computer needs to be taught to \u201cread.\u201d This requires the same patience and skill required to teach a young child to recognize letters, then words and sentences, and finally complex thoughts.<\/p>\r\n PACI needed to establish a \u201cground truth,\u201d a common geospatial framework that would encompass the existing database. After much trial-and-error, the staff was able to train using 75 square kilometers of data to provide input for the model to scan 3,000 square kilometers of satellite imagery.<\/p>\r\n <\/p>\r\n Knowing the Local Vocabulary Pays Off<\/strong><\/p>\r\n For PACI, the main challenge was giving the program enough information to recognize buildings and streets.\u201cThe contrast between land, streets, and buildings, was very minimal,\u201d Abdel Karim explained. \u201cIt\u2019s hard even for a person to differentiate among them by eye. And our threshold for saying that our model worked was very high.\u201d<\/p>\r\n Often, with shadows cast by the sweltering summer sun, building footprints did not easily align with the images captured by the satellite. The darkened overlapping edges often confused the program.<\/p>\r\n Streets posed their own unique problem. They had to be recognizable individually, but also as part of a coherent grid. PACI\u2019s staff had to ensure that all streets in the imagery were connected by common \u201ccenter lines\u201d\u2014and that the lines in the new images fit seamlessly with those in the existing street network.<\/p>\r\n \u201cYou really have to take your local experience and use it as a \u2018flavor\u2019 on top of the satellite imagery,\u201d Abdel Karim said. \u201cThat\u2019s what makes it possible for machine learning to perform these calculations.\u201d<\/p>\r\n <\/p>\r\n <\/p>\r\n The teaching process required serious work. But once the machine learning model was ready, the rest was a relative breeze. PACI devoted time to training and fine tuning the model, knowing that this work would pay dividends into the future.<\/p>\r\n The model and training data set can be used today to update the database in about three hours and provide even more accurate maps than before. And this model will live on and can continue to be modified and enhanced by PACI into the future, taking into consideration new architecture styles, building types or other new features.<\/p>\r\n <\/p>\r\n![](\"https:\/\/www.esrith.com\/wp-content\/uploads\/2021\/11\/Buildings_Comparison-768x308-600x241.jpg\")
<\/p>\r\n![](\"https:\/\/www.esrith.com\/wp-content\/uploads\/2021\/11\/Buildings_Roads_2-768x432-539x303.jpg\")
<\/p>\r\n