Abstract. Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth system models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here, we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning (ML) techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of peatland formation and include spatially distributed climate, geomorphological and soil data, and remotely sensed vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualitative comparisons to other maps in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r2 of 0.73 with a root-mean-square error and mean bias error of 9.11 % and −0.36 %, respectively. Our second error estimate was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping products generated through more traditional approaches, at least for boreal peatlands.

Autonomous selective spraying could be a way for agriculture to reduce production costs, save resources, protect the environment and help to fulfill specific pesticide regulations. The objective of this paper was to investigate the use of a low-cost sonar sensor for autonomous selective spraying of single plants. For this, a belt driven autonomous robot was used with an attached 3-axes frame with three degrees of freedom. In the tool center point (TCP) of the 3-axes frame, a sonar sensor and a spray valve were attached to create a point cloud representation of the surface, detect plants in the area and perform selective spraying. The autonomous robot was tested on replicates of artificial crop plants. The location of each plant was identified out of the acquired point cloud with the help of Euclidian clustering. The gained plant positions were spatially transformed from the coordinates of the sonar sensor to the valve location to determine the exact irrigation points. The results showed that the robot was able to automatically detect the position of each plant with an accuracy of 2.7 cm and could spray on these selected points. This selective spraying reduced the used liquid by 72%, when comparing it to a conventional spraying method in the same conditions.

Abstract. Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed by Earth System Models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here, we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of peatland formation and include spatially distributed climate, geomorphological and soil data, along with remotely-sensed vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualitative comparisons to other maps in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r2 of 0.73 with a root mean squared error and mean bias error of 9.11 % and −0.36 %, respectively. Our second error estimate was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping products generated through more traditional approaches, at least for boreal peatlands.

<p>Flooded savannas are extensive in South America and this study was conducted to assess two digital soil mapping (DSM) approaches to predict the spatial distribution of soil organic carbon (SOC) content and stocks in the Orinoco flooded savannas of Casanare department, located in the eastern plains of Colombia. SOC was estimated using a total of 80 sites sampled at two soil depth intervals (0-10 cm and 10-30 cm). SOC ranged from 0.41% at 0-10 cm and 0.23% at 10-30 cm in drier soils found in continental dunes with sandy textures and low vegetation cover (steppe) to over 14.50% and 7.51% in soils that experienced seasonal flooding located in depressions with loamy textures and flooded savanna vegetation. Predictions of the spatial distribution of SOC were done through Expert Knowledge (EK) and Random Forest (RF) approaches across the study area at 0-10 cm and 10-30 cm soil depth. Both DSM approaches were assessed through root mean square errors, mean absolute errors, and coefficients of determination. Although both DSM approaches performed very well, EK was considered slightly superior to predict SOC in the Casanare flooded savannas. Covariates derived from vegetation coverage, topography, and soil texture properties were identified as key drivers in controlling its distribution at the study area. We found total SOC stocks of 55.07 Mt with a mean density of 83.13 ± 24.32 t ha<sup>-1</sup> stored in the first 30 cm soil depth, with 12.3% of this being located in the flooded parts of the savanna landscape, which represented only 7.9% of the study area (664,752 ha). This study provides the first effort to systematically quantify SOC stocks in the Casanare flooded savannas and shows the importance of conserving this ecosystem with the aim of avoiding SOC losses and consequent increased CO<sub>2</sub> emissions to the atmosphere. We estimate that the department of Casanare would release an average of 2,42 Mton of CO<sub>2</sub> emissions per year over 30 years if there were large scale conversion of the flooded savannas to intensive agriculture, which corresponds to 62% of the current emissions of the department. At regional level, the impact of a large-scale land use conversion of the flooded Llanos del Orinoco ecosystem area (15 Mha) would represent 1/3 of the current net Colombian CO<sub>2</sub> emission (AFOLU), which makes this region a potentially important source of emissions if correct decisions are not taken regarding the land management.</p>

In Colombia, the rise of agricultural and pastureland expansion continues to exert increasing pressure on the structure and ecological processes of savannahs in the Eastern Plains. However, the effect of land use change on soil properties is often unknown due to poor access to remote areas. Effective management and conservation of soils requires the development spatial approaches that measure and predict dynamic soil properties such as soil organic carbon (SOC). This study estimates the SOC stock in the Eastern Plains of Colombia, with validation and uncertainty analyses, using legacy data of 653 soil samples. A random forest model of nine environmental covariate layers was used to develop predictions of SOC content. Model validation was determined using the Taylor series method, and root-mean-squared error (RMSE) and mean error (ME) were calculated to assess model performance. We found that the model explained 50.28% of the variation within digital SOC content map. Raster layers of SOC content, bulk density, and coarse rock fragment within the Eastern Plains were used to calculate SOC stock within the region. With uncertainty, SOC stock in the topsoil of the Eastern Plains was 1.2 G t ha−1. We found that SOC content contributed nearly all the uncertainty in the SOC stock predictions, although better determinations of SOC stock can be obtained with the use of a more geomorphological diverse dataset. The digital soil maps developed in this study provide predictions of extant SOC content and stock in the topsoil of the Eastern Plains, important soil information that may provide insight into the development of research, regulatory, and legislative initiatives to conserve and manage this evolving ecosystem.