Geospatial dataset on deforestation and urban sprawl in Dhaka, Bangladesh: A resource for environmental analysis

Abstract

This dataset comprises high-resolution satellite images for monitoring deforestation in Dhaka, Bangladesh. Data were acquired via Google Earth Pro from fixed locations to maintain consistency in observing tree cover alterations. Each image includes annotations and JSON mask files that delineate tree cover and deforested areas. The dataset facilitates machine learning applications, including object detection, semantic segmentation, and change detection. Image resolution and aspect ratio vary, with 5-35 images recorded per location annually over a decade. This data serves researchers investigating urbanization's environmental impact and the gradual reduction of tree cover in a rapidly evolving urban environment. Utilizing the annotations and masks enables the training of machine learning models to identify and forecast vegetation changes, aiding environmental monitoring and conservation initiatives. Furthermore, the dataset is readily applicable for educational purposes in disciplines such as geography, environmental science, and machine learning. It provides critical insights into the application of machine learning and image processing in addressing real-world environmental issues.

Keywords: Computer vision; Deep learning; Image classification; Semantic segmentation.

Fig. 1

Sample of original image.

Fig. 2

Green percentage from 2010 to 2021.

Fig. 3

Data structure of the dataset.

Fig. 4

Workflow of the dataset creation.

Fig. 5

Sample of image annotating with make sense AI picture.

Fig. 6

Sample of mask picture.

Fig. 7

Accuracy and loss of U-Net model.

Fig. 8

Confusion matrix of U-Net model.

Fig. 9

Predicted mask of U-Net.