Identifying Wetland Areas in Historical Maps using Deep Convolutional Neural Networks

TL;DR

This paper demonstrates that deep convolutional neural networks can effectively identify and digitize historical wetlands from hand-drawn maps, producing valuable GIS layers for studying land-use change over the past century.

Contribution

The study introduces a CNN-based method for extracting historical wetland locations from maps, achieving high accuracy and providing open GIS resources for historical land-use analysis.

Findings

CNN achieved an F1-score of 0.886 in wetland identification.

Generated GIS layers of historical wetlands are publicly available.

Method demonstrates potential for digitizing non-textual historical map data.

Abstract

1) The local environment and land usages have changed a lot during the past one hundred years. Historical documents and materials are crucial in understanding and following these changes. Historical documents are, therefore, an important piece in the understanding of the impact and consequences of land usage change. This, in turn, is important in the search of restoration projects that can be conducted to turn and reduce harmful and unsustainable effects originating from changes in the land-usage. 2) This work extracts information on the historical location and geographical distribution of wetlands, from hand-drawn maps. This is achieved by using deep learning (DL), and more specifically a convolutional neural network (CNN). The CNN model is trained on a manually pre-labelled dataset on historical wetlands in the area of J\"onk\"oping county in Sweden. These are all extracted from the historical map called "Generalstabskartan". 3) The presented CNN performs well and achieves a $F_1$-score of 0.886 when evaluated using a 10-fold cross validation over the data. The trained models are additionally used to generate a GIS layer of the presumable historical geographical distribution of wetlands for the area that is depicted in the southern collection in Generalstabskartan, which covers the southern half of Sweden. This GIS layer is released as an open resource and can be freely used. 4) To summarise, the presented results show that CNNs can be a useful tool in the extraction and digitalisation of non-textual information in historical documents, such as historical maps. A modern GIS material that can be used to further understand the past land-usage change is produced within this research.