A Continental-Scale Assessment of Density, Size, Distribution and Historical Trends of Farm Dams Using Deep Learning Convolutional Neural Networks

Abstract

Farm dams are a ubiquitous limnological feature of agricultural landscapes worldwide. While their primary function is to capture and store water, they also have disproportionally large effects on biodiversity and biogeochemical cycling, with important relevance to several Sustainable Development Goals (SDGs). However, the abundance and distribution of farm dams is unknown in most parts of the world. Therefore, we used artificial intelligence and remote sensing data to address this critical global information gap. Specifically, we trained a deep learning convolutional neural network (CNN) on high-definition satellite images to detect farm dams and carry out the first continental-scale assessment on density, distribution and historical trends. We found that in Australia there are 1.765 million farm dams that occupy an area larger than Rhode Island (4678 km2) and store over 20 times more water than Sydney Harbour (10,990 GL). The State of New South Wales recorded the highest number of farm dams (654,983; 37% of the total) and Victoria the highest overall density (1.73 dams km−2). We also estimated that 202,119 farm dams (11.5%) remain omitted from any maps, especially in South Australia, Western Australia and the Northern Territory. Three decades of historical records revealed an ongoing decrease in the construction rate of farm dams, from >3% per annum before 2000, to ~1% after 2000, to <0.05% after 2010—except in the Australian Capital Territory where rates have remained relatively high. We also found systematic trends in construction design: farm dams built in 2015 are on average 50% larger in surface area and contain 66% more water than those built in 1989. To facilitate sharing information on sustainable farm dam management with authorities, scientists, managers and local communities, we developed AusDams.org—a free interactive portal to visualise and generate statistics on the physical, environmental and ecological impacts of farm dams.

A New Method Based on a Multilayer Perceptron Network to Determine In-Orbit Satellite Attitude for Spacecrafts without Active ADCS Like UVSQ-SAT

“…Then, we select the measurements from the sensors that are facing the Sun with a minimal angle of about 60 degrees (in a 120 degrees field of view). The measurements are then corrected using the dot product between the Sun's direction and the normal vector relatively to each of the faces of the CubeSat facing the Sun (see Equations (10) and (11)). This parameter is directly linked to the attitude of the satellite recovered previously.…”

“…Deep learning algorithms are often used for remote sensing applications [10]. Neural networks are implemented using satellite data for detect farms or to classify lands as in [11][12][13][14]. This technique appears to be really convenient in the remote sensing field.…”

Mapping and Monitoring the Multi-Decadal Dynamics of Australia’s Open Waterbodies Using Landsat

“…Insights into the growth of waterbodies within a region provide an independent assessment of infrastructure growth, and can be used to verify the installation of approved works and potentially flag unapproved works as well. A recent paper by Malerba et al [59] used DEA Waterbodies to explore the rate of large storage construction across Australia since 1987.…”

Increased livestock weight gain from improved water quality in farm dams: A cost-benefit analysis

“…For example, the Murray-Darling Basin, the most important food production region in Australia, supports more than 650 000 farm dams that provide domestic livestock access to drinking water [ 5 ]. Continent-wide, there is an estimated 1.765m farm dams in Australia [ 7 ].…”