Convolutional neural network for high-resolution wetland mapping with open data: Variable selection and the challenges of a generalizable model.

Landscape scale wetland conservation requires accurate, up-to-date wetland maps. The most useful approaches to creating such maps are automated, spatially generalizable, temporally repeatable, and can be applied at large spatial scales. However, mapping wetlands with predictive models is challenging due to the highly variable characteristics of wetlands in both space and time. Currently, most approaches are limited by coarse resolution, commercial data, and geographic specificity. Here, we trained a deep learning model and evaluated its ability to automatically map wetlands at landscape scale in a variety of geographies. We trained a U-Net architecture to map wetlands at 1-meter spatial resolution with the following remotely sensed covariates: multispectral data from the National Agriculture Imagery Program and the Sentinel-2 satellite system, and two LiDAR-derived datasets, intensity and geomorphons. The full model mapped wetlands accurately (94 % accuracy, 96.5 % precision, 95.2 % AUC) at 1-meter resolution. Post hoc model evaluation showed that the model correctly predicted wetlands even in areas that had incorrect label/training data, which penalized the recall rate (90.2 %). Applying the model in a new geography resulted in poor performance (precision = ~80 %, recall = 48 %). However, limited retraining in this geography improved model performance substantially, demonstrating an effective means to create a spatially generalizable model. We demonstrate wetlands can be mapped at high-resolution (1 m) using free data and efficient deep-learning models that do not require manual feature engineering. Including LiDAR and geomorphons as input data improved model accuracy by 2 %, and where these data are unavailable a simpler model can efficiently map wetlands. Given the dynamic nature of wetlands and the important ecosystem services they provide, high-resolution mapping can be a game changer in terms of informing restoration and development decisions.

Natural climate solutions.

Better stewardship of land is needed to achieve the Paris Climate Agreement goal of holding warming to below 2 °C; however, confusion persists about the specific set of land stewardship options available and their mitigation potential. To address this, we identify and quantify "natural climate solutions" (NCS): 20 conservation, restoration, and improved land management actions that increase carbon storage and/or avoid greenhouse gas emissions across global forests, wetlands, grasslands, and agricultural lands. We find that the maximum potential of NCS-when constrained by food security, fiber security, and biodiversity conservation-is 23.8 petagrams of CO2 equivalent (PgCO2e) y-1 (95% CI 20.3-37.4). This is ≥30% higher than prior estimates, which did not include the full range of options and safeguards considered here. About half of this maximum (11.3 PgCO2e y-1) represents cost-effective climate mitigation, assuming the social cost of CO2 pollution is ≥100 USD MgCO2e-1 by 2030. Natural climate solutions can provide 37% of cost-effective CO2 mitigation needed through 2030 for a >66% chance of holding warming to below 2 °C. One-third of this cost-effective NCS mitigation can be delivered at or below 10 USD MgCO2-1 Most NCS actions-if effectively implemented-also offer water filtration, flood buffering, soil health, biodiversity habitat, and enhanced climate resilience. Work remains to better constrain uncertainty of NCS mitigation estimates. Nevertheless, existing knowledge reported here provides a robust basis for immediate global action to improve ecosystem stewardship as a major solution to climate change.

The last frontiers of wilderness: Tracking loss of intact forest landscapes from 2000 to 2013.

An intact forest landscape (IFL) is a seamless mosaic of forest and naturally treeless ecosystems with no remotely detected signs of human activity and a minimum area of 500 km2. IFLs are critical for stabilizing terrestrial carbon storage, harboring biodiversity, regulating hydrological regimes, and providing other ecosystem functions. Although the remaining IFLs comprise only 20% of tropical forest area, they account for 40% of the total aboveground tropical forest carbon. We show that global IFL extent has been reduced by 7.2% since the year 2000. An increasing rate of global IFL area reduction was found, largely driven by the tripling of IFL tropical forest loss in 2011-2013 compared to that in 2001-2003. Industrial logging, agricultural expansion, fire, and mining/resource extraction were the primary causes of IFL area reduction. Protected areas (International Union for Conservation of Nature categories I to III) were found to have a positive effect in slowing the reduction of IFL area from timber harvesting but were less effective in limiting agricultural expansion. The certification of logging concessions under responsible management had a negligible impact on slowing IFL fragmentation in the Congo Basin. Fragmentation of IFLs by logging and establishment of roads and other infrastructure initiates a cascade of changes that lead to landscape transformation and loss of conservation values. Given that only 12% of the global IFL area is protected, our results illustrate the need for planning and investment in carbon sequestration and biodiversity conservation efforts that target the most valuable remaining forests, as identified using the IFL approach.