Enhancing surface drainage mapping in eastern Canada with deep learning applied to LiDAR-derived elevation data

Agricultural dykelands in Nova Scotia rely heavily on a surface drainage technique called land forming, which is used to alter the topography of fields to improve drainage. The presence of land-formed fields provides useful information to better understand land utilization on these lands vulnerable to rising sea levels. Current field boundaries delineation and classification methods, such as manual digitalization and traditional segmentation techniques, are labour-intensive and often require manual and time-consuming parameter selection. In recent years, deep learning (DL) techniques, including convolutional neural networks and Mask R-CNN, have shown promising results in object recognition, image classification, and segmentation tasks. However, there is a gap in applying these techniques to detecting surface drainage patterns on agricultural fields. This paper develops and tests a Mask R-CNN model for detecting land-formed fields on agricultural dykelands using LiDAR-derived elevation data. Specifically, our approach focuses on identifying groups of pixels as cohesive objects within the imagery, a method that represents a significant advancement over pixel-by-pixel classification techniques. The DL model developed in this study demonstrated a strong overall performance, with a mean Average Precision (mAP) of 0.89 across Intersection over Union (IoU) thresholds from 0.5 to 0.95, indicating its effectiveness in detecting land-formed fields. Results also revealed that 53% of Nova Scotia's dykelands are being used for agricultural purposes and approximately 75% (6924 hectares) of these fields were land-formed. By applying deep learning techniques to LiDAR-derived elevation data, this study offers novel insights into surface drainage mapping, enhancing the capability for precise and efficient agricultural land management in regions vulnerable to environmental changes.

The impact of coastal realignment on the availability of ecosystem services: gains, losses and trade-offs from a local community perspective

Coastal realignment is the procedure of repositioning or removing coastal defense structures to restore tidal flooding and facilitate the development of intertidal ecosystems in a previously reclaimed area from the sea. A key policy objective of coastal realignment is to increase ecosystem services provided by intertidal ecosystems and thereby contribute to human well-being. However, the social response to coastal realignment is often negative, raising the question as to what extent communities living nearby project locations recognize, value and benefit from the goods and services provided by restored intertidal ecosystems. In this study, we examine public perceptions of ecosystem services gains, losses and trade-offs associated with coastal realignment. We hereby focus on three coastal realignment case study locations in the Southwest delta, the Netherlands. Questionnaires were administered in nearby villages and the collected data (N = 261) were analyzed using random forest regression models. A notable outcome of this study is that local communities often consider coastal realignment interventions to decrease rather than increase the availability of ecosystem services. This points to a discrepancy between how coastal realignment is viewed from a policy perspective and a local community perspective. Changes in the availability of cultural ecosystem services were found to have the highest impact on the level of support for coastal realignment, while the importance attached to provisioning, regulating and supporting ecosystem services was notably lower. In consequence, to increase public support, it will be essential to minimize the loss of cultural ecosystem services, or better yet, find ways to increase cultural ecosystem services through coastal realignment, for instance by creating opportunities for recreation and tourism.

Disturbance of primary producer communities disrupts the thermal limits of the associated aquatic fauna

Environmental fluctuation forms a framework of variability within which species have evolved. Environmental fluctuation includes predictability, such as diel cycles of aquatic oxygen fluctuation driven by primary producers. Oxygen availability and fluctuation shape the physiological responses of aquatic animals to warming, so that, in theory, oxygen fluctuation could influence their thermal ecology. We describe annual oxygen variability in agricultural drainage channels and show that disruption of oxygen fluctuation through dredging of plants reduces the thermal tolerance of freshwater animals. We compared the temperature responses of snails, amphipods, leeches and mussels exposed to either natural oxygen fluctuation or constant oxygen in situ under different acclimation periods. Oxygen saturation in channel water ranged from c. 0 % saturation at night to >300 % during the day. Temperature showed normal seasonal variation and was almost synchronous with daily oxygen fluctuation. A dredging event in 2020 dramatically reduced dissolved oxygen variability and the correlation between oxygen and temperature was lost. The tolerance of invertebrates to thermal stress was significantly lower when natural fluctuation in oxygen availability was reduced and decoupled from temperature. This highlights the importance of natural cycles of variability and the need to include finer scale effects, including indirect biological effects, in modelling the ecosystem-level consequences of climate change. Furthermore, restoration and management of primary producers in aquatic habitats could be important to improve the thermal protection of aquatic invertebrates and their resistance to environmental variation imposed by climate change.