Machine-learning model to delineate sub-surface agricultural drainage from satellite imagery.

Knowing subsurface drainage (tile-drain) extent is integral to understanding how landscapes respond to precipitation events and subsequent days of drying, as well as how soil characteristics and land management influence stream response. Consequently, a time series of tile-drain extent would inform one aspect of land management that complicates our ability to explain streamflow and water-quality as a function of climate variability or conservation management. We trained a UNet machine-learning model, a convolutional neural network designed to highlight objects of interest within an image, to delineate tile-drain networks in panchromatic satellite imagery without additional data on soils, topography, or historical tile-drain extent. This was done by training the model to match the accuracy of human experts manually tracing the surface representation of tile drains in satellite imagery. Our approach began with a library of images that were used to train and quantify the accuracy of the model, with model performance tested on imagery from two areas that were not used to train the model. Satellite imagery included acquisition dates from 2008 to 2020. Training imagery was from agricultural areas within the US Great Lakes basin. Validation imagery was from the upper Maumee River, tributary to western Lake Erie, and an Indiana, Ohio-River headwater tributary. Our analysis of the satellite imagery paired with meteorological and soil data found that during spring, a combination of relatively high solar radiation, intermediate soil-water content and bare fields enabled the best model performance. Each area of interest was heavily tile-drained, where better understanding the movement of water, nutrients, and sediment from fields to downstream water bodies is key to managing harmful algal blooms and hypoxia. The trained UNet model successfully identified tile drains visible in the validation imagery with an accuracy of 93%-96% and balanced accuracy of 52%-54%, similar to performance for training data (95% and 63%, respectively). Model performance will benefit from ongoing contributions to the training library.

Mapping of Agricultural Subsurface Drainage Systems Using Unmanned Aerial Vehicle Imagery and Ground Penetrating Radar.

Agricultural subsurface drainage systems are commonly installed on farmland to remove the excess water from poorly drained soils. Conventional methods for drainage mapping such as tile probes and trenching equipment are laborious, cause pipe damage, and are often inefficient to apply at large spatial scales. Knowledge of locations of an existing drainage network is crucial to understand the increased leaching and offsite release of drainage discharge and to retrofit the new drain lines within the existing drainage system. Recent technological developments in non-destructive techniques might provide a potential alternative solution. The objective of this study was to determine the suitability of unmanned aerial vehicle (UAV) imagery collected using three different cameras (visible-color, multispectral, and thermal infrared) and ground penetrating radar (GPR) for subsurface drainage mapping. Both the techniques are complementary in terms of their usage, applicability, and the properties they measure and were applied at four different sites in the Midwest USA. At Site-1, both the UAV imagery and GPR were equally successful across the entire field, while at Site-2, the UAV imagery was successful in one section of the field, and GPR proved to be useful in the other section where the UAV imagery failed to capture the drainage pipes' location. At Site-3, less to no success was observed in finding the drain lines using UAV imagery captured on bare ground conditions, whereas good success was achieved using GPR. Conversely, at Site-4, the UAV imagery was successful and GPR failed to capture the drainage pipes' location. Although UAV imagery seems to be an attractive solution for mapping agricultural subsurface drainage systems as it is cost-effective and can cover large field areas, the results suggest the usefulness of GPR to complement the former as both a mapping and validation technique. Hence, this case study compares and contrasts the suitability of both the methods, provides guidance on the optimal survey timing, and recommends their combined usage given both the technologies are available to deploy for drainage mapping purposes.

Mapping of Agricultural Subsurface Drainage Systems Using a Frequency-Domain Ground Penetrating Radar and Evaluating Its Performance Using a Single-Frequency Multi-Receiver Electromagnetic Induction Instrument.

Subsurface drainage systems are commonly used to remove surplus water from the soil profile of a poorly drained farmland. Traditional methods for drainage mapping involve the use of tile probes and trenching equipment that are time-consuming, labor-intensive, and invasive, thereby entailing an inherent risk of damaging the drainpipes. Effective and efficient methods are needed in order to map the buried drain lines: (1) to comprehend the processes of leaching and offsite release of nutrients and pesticides and (2) for the installation of a new set of drain lines between the old ones to enhance the soil water removal. Non-invasive geophysical soil sensors provide a potential alternative solution. Previous research has mainly showcased the use of time-domain ground penetrating radar, with variable success, depending on local soil and hydrological conditions and the central frequency of the specific equipment used. The objectives of this study were: (1) to test the use of a stepped-frequency continuous wave three-dimensional ground penetrating radar (3D-GPR) with a wide antenna array for subsurface drainage mapping and (2) to evaluate its performance with the use of a single-frequency multi-receiver electromagnetic induction (EMI) sensor in-combination. This sensor combination was evaluated on twelve different study sites with various soil types with textures ranging from sand to clay till. While the 3D-GPR showed a high success rate in finding the drainpipes at five sites (sandy, sandy loam, loamy sand, and organic topsoils), the results at the other seven sites were less successful due to the limited penetration depth of the 3D-GPR signal. The results suggest that the electrical conductivity estimates produced by the inversion of apparent electrical conductivity data measured by the EMI sensor could be a useful proxy for explaining the success achieved by the 3D-GPR in finding the drain lines.

Laboratory comparison of four iron-based filter materials for water treatment of trace element contaminants.

A laboratory investigation provided preliminary comparison of trace element contaminant water treatment capabilities for four iron-based filter materials. The iron-based filter materials tested were zero-valent iron (ZVI), porous iron composite (PIC), sulfur modified iron (SMI), and iron oxide/hydroxide (IOH). Two types of trace element contaminant solutions were tested, one combined As, Cr, and Se (added as AsO4(3-), CrO4(2-), and SeO4(2-), respectively), while the second combined Cd2+, Cu2+, and Pb2+. The laboratory investigation included saturated falling-head hydraulic conductivity tests, contaminant removal-desorption/dissolution batch tests, and low-to-high flow rate saturated solute transport column tests. Hydraulic conductivity test results indicate that all four iron-based filter materials have sufficient water flow capacity as indicated by saturated hydraulic conductivity values greater than 1 x 10(-2) cm/s. Essentially, 100% of each trace element (As, Cd, Cr, Cu, Pb, and Se) was removed by SMI during the contaminant removal portion of the batch tests and during the column tests, while IOH exhibited good removal of each trace element except Se. Results from the contaminant removal portion of the batch tests and from the column tests showed ZVI and PIC were effective in treating Cd, Cr, Cu, and Pb. With the exception of Se adsorption/precipitation onto IOH, the desorption/dissolution portion of the batch tests showed that once As, Cd, Cr, Cu, Pb, or Se are adsorbed/precipitated onto ZVI, PIC, SMI, or IOH particle surfaces, these trace elements are then not readily desorbed or dissolved back into solution.

Laboratory comparison of four iron-based filter materials for drainage water phosphate treatment.

A laboratory investigation evaluated phosphate (PO4(3-)) drainage water treatment capabilities of four iron-based filter materials. The iron-based filter materials tested were zero-valent iron (ZVI), porous iron composite (PIC), sulfur modified iron (SMI), and iron oxide/ hydroxide (IOH). Only filter material retained on a 60-mesh sieve (> 0.25 mm) was used for evaluation. The laboratory investigation included saturated falling-head hydraulic conductivity tests, contaminant removal or desorption/dissolution batch tests, and low-to-high flow rate saturated solute transport column tests. Each of the four iron-based filter materials have sufficient water flow capacity as indicated by saturated hydraulic conductivity values that in most cases were greater than 1 x 10(-2) cm/s. For the 1, 10, and 100 ppm PO4(3-)-P contaminant removal batch tests, each of the four iron-based filter materials removed at least 95% of the PO4(3-)-P originally present. However, for the 1000 ppm PO4(3-)-P contaminant removal batch tests, IOH by far exhibited the greatest removal effectiveness (99% PO4(3-)-P removal), followed by SMI (72% PO4(3-)-P removal), then ZVI (62% PO4(3-)-P removal), and finally PIC (15% PO4(3-)-P removal). The desorption/dissolution batch test results, especially with respect to SMI and IOH, indicate that once PO4(3-) is adsorbed/precipitated onto surfaces of iron-based filter material particles, this PO4(3-) becomes fixed and is then not readily desorbed/dissolved back into solution. The results from the column tests showed that regardless of low or high flow rate (contact time ranged from a few hours to a few minutes) and PO4(3-) concentration (1 ppm or 10 ppm PO4(3-)-P), PIC, SMI, and IOH reduced PO4(3-)-P concentrations to below detection limits, while ZVI removed at least 90% of the influent PO4(3-)-P. Consequently, these laboratory results indicate that the ZVI, PIC, SMI, and IOH filter materials all exhibit promise for phosphate drainage water treatment.