Dr Najarij Bulawka, along with Dr Hèctor A. Orengo and Dr Iban Berganzo-Besga, have published a new open access paper on the application of deep learning in the study of qanats in arid environments. The paper is published in the journal “Journal of Archaeological Science”:
Buławka, Nazarij, Hector A. Orengo, and Iban Berganzo-Besga. 2024. ‘Deep Learning-Based Detection of Qanat Underground Water Distribution Systems Using HEXAGON Spy Satellite Imagery’. Journal of Archaeological Science 171:106053
Link to free downloaded: https://www.sciencedirect.com/science/article/pii/S0305440324001213
Highlights:
Object Detection model (YOLOv9) for mapping qanat systems using spy satellite images.
Higher accuracy with an approach focused on qanats arranged in lines.
The trained model is a global detector, validated with qanats in other countries.
Implemented automatic methods to filter out isolated false detections.
Abstract
Qanats are a remarkable type of ancient hydraulic structure for sustainable water distribution in arid environments that use subterranean channels to transport water from highland or mountainous areas. The presence of the qanat system is marked by a line of regularly spaced shafts visible from the surface, which can be used to detect qanats using satellite imagery. Typically, qanats have been documented by field mapping or manual digitisation within a Geographic Information System (GIS) environment. This process is time-consuming due to the numerous shafts within each qanat line. However, several automated methods for detecting qanat structures have been explored, using techniques such as morphological filters, custom convolutional neural networks (CNN) and, more recently, YOLOv5 and Mask R-CNN. These approaches used high-resolution RGB images and CORONA images. However, the use of black and white CORONA in CNNs has been limited in its applicability due to a high rate of false positives.
This paper explores the potential of YOLOv9 in processing the black and white HEXAGON (KH-9) high-resolution spy satellite system launched in 1971. Two areas in Afghanistan (Maiwand) and Iran (Gorgan Plain) were selected to train the system images extracted from HEXAGON imagery and artificial synthetic data. The training dataset was augmented using the Albumentation library, which increased the number of tiles used. The model was tested using two types of HEXAGON imagery for selected areas in Afghanistan (Maiwand), Iran (Gorgan Plain) and Morocco (Rissani), and CORONA imagery in Iran (Gorgan Plain).
Our study provided a model capable of predicting the location of qanat shafts with a precision of over 0.881 and a recall of 0.627 for most of the case studies tested. This is the first case study aimed at detecting qanats in different landscapes using different types of satellite imagery. Using real, augmented, and artificial data allowed us to generalise the representation of qanats into lineal groups of circular features. Thanks to applying labelling for individual qanats and their pairs as separate classes, our approach eliminated most of the isolated and clustered false positives.
