A novel automated labelling algorithm for deep learning-based built-up areas extraction using nighttime lighting data

• Introduced a pioneering method for generating label sets for deep learning-based built-up areas extraction (BUAE) using nighttime lighting data. • Identified and addressed the limitations of directly utilising nighttime lighting data with varied intensity ranges for label set production. • An algorithm for optimized label generation without human involvement was developed and tested in eight different environment layout cities, most of that achieving over 90% accuracy in BUAE. • The capabilities of DeeplabV3 and U-Net in BUAE exhibit distinct differences, each with its own advantages and disadvantages. • Summarise the limitations of new methods and future directions. The use of remote sensing imagery and cutting-edge deep learning techniques can produce impressive results when it comes to built-up areas extraction (BUAE). However, reducing the manual labelling set production process while ensuring high accuracy is currently the main research topic. This study pioneers the exploitation of nighttime lighting data (NLD) for automatically generating deep learning label sets, assessing the feasibility, and identifying limitations of using varied intensity ranges of lighting data directly for this purpose. We provide a novel method for generating fine-grained labels through an optimisation technique that eliminates the necessity for human involvement. This approach employs deep learning segmentation algorithms and has been tested in eight cities across seven countries. The results indicate that segmentation performs well in most cities, with the combination of iso clustering and NLD allowing for more precise extraction of urban building districts. The overall accuracy exceeds 90% in most cities. The results based on manual and historical data (around 0.7) as labels are significantly lower than those based on NLD. At the same time, the segmentation effect of deep learning has a more significant advantage over traditional machine learning classification algorithms (around 0.8). DeeplabV3 and U-Net exhibit different strengths in segmentation and extraction: DeeplabV3 has a stronger ability to eliminate errors, while U-Net retains the capability to handle less labelled information, making them mutually advantageous depending on the specific requirements of the task. It proposes a Strategy to automatically extract built-up areas with minimal human involvement.