Advances in remote sensing of the early Anthropocene in tropical wetlands: From biplanes to lidar and machine learning

Abstract

This paper reviews the history of remote sensing for mapping ancient Maya wetland fields in Central America and provides a new assessment using machine learning with LiDAR data. We evaluate past uses of radar, multispectral, and LiDAR datasets in Northwest Belize across well-studied wetland field complexes that occur under different vegetation conditions. Next, we compare topographic products derived from LiDAR data commonly used for archaeology and geomorphology. Lastly, we train a machine learning algorithm to detect ancient canals with LiDAR data and test the algorithm on a newly rediscovered field system. The spatial resolution of any dataset must be sufficiently high (2-m or finer resolution) to detect most of these canals reliably. High resolution multispectral sensors can detect canals in open areas, but most wetland complexes are under dense tropical forest impenetrable to multispectral instruments. LiDAR data were the most useful due to the high spatial resolution (0.5-m) and the ability to penetrate canopy, but still have limitations under certain conditions. The intensity of the LiDAR returns with multispectral LiDAR systems can reveal differences in soil and vegetation between ancient canals and fields in places leveled by modern farmers. The algorithm successfully maps ancient canals but has many false positives in natural depressions and drainages. Although the machine learning approach tested here cannot be used on its own, we used it with the LiDAR visualizations to refine the canal estimates from previous studies, mapping nearly 50% more canals in the Central Rio Bravo floodplain than originally published.

Validating predictions of burial mounds with field data: the promise and reality of machine learning

“…Even many successful ML applications require significant human intervention either in the form of crowdsourcing or specialist work (see, e.g. Casini et al, 2023;Doyle et al, 2023;Verschoof-van der Vaart and Lambers, 2019). As a result of challenges like these, Casana (2020), goes so far as to reject ML approaches entirely, instead favouring "brute force" manual inspection of satellite imagery by experts.…”

“…Enthusiasm arising from this study, and similar outcomes from Egypt (Woolf, 2018) must, however, be tempered by the fact that the authors targeted uniform features situated in environments with little variation in terrain or vegetationindeed, with relatively little vegetation or other confounding factors at all. Fewer studies explore the challenges presented by more difficult environments where cultural heritage lies in diverse or thick vegetation, surrounded by obtrusive natural and artificial features (Doyle et al, 2023;Fuentes-Carbajal et al, 2023;Verschoof-van der Vaart et al, 2020).…”

Soil toposequences, soil erosion, and ancient Maya land use adaptations to pedodiversity in the tropical karstic landscapes of southern Mexico

“…Finally, this interplay controls the spatial distribution of soil characteristics vital for ancient Maya subsistence: physical and chemical soil quality, fertility, mechanical stability, etc., which largely define the mode and differentiation of land use. In turn, ancient land use practices modified this interplay, hampering certain processes and accelerating others, which profoundly modified soil mantle and had feedback effects on the ancient economy and social dynamics (Beach et al, 2006;Carozza et al, 2007;Turner and Sabloff, 2012;Beach et al, 2015;Dunning et al, 2020;Doyle et al, 2023).…”

UAV-Based Remote Sensing for Detection and Visualization of Partially-Exposed Underground Structures in Complex Archaeological Sites

“…Complex 3D reconstruction (e.g., establishing reliable matchings in overlapping imagery). [4,18,21,30,31] LiDAR-based…”

“…Less semantic information. [28,30] (a) (b) In spite of the above characteristics of LiDAR data, the detection of underground structures (including cisterns) from point clouds remains a challenging task, especially when dealing with complex archaeological sites exhibiting steep slopes and dense vegetation [32][33][34]. The detection of cisterns is quite important for some archaeological sites, especially those in areas with limited access to fresh water.…”