Study becomes insight: Ecological learning from machine learning.

The ecological and environmental science communities have embraced machine learning (ML) for empirical modelling and prediction. However, going beyond prediction to draw insights into underlying functional relationships between response variables and environmental 'drivers' is less straightforward. Deriving ecological insights from fitted ML models requires techniques to extract the 'learning' hidden in the ML models.We revisit the theoretical background and effectiveness of four approaches for deriving insights from ML: ranking independent variable importance (Gini importance, GI; permutation importance, PI; split importance, SI; and conditional permutation importance, CPI), and two approaches for inference of bivariate functional relationships (partial dependence plots, PDP; and accumulated local effect plots, ALE). We also explore the use of a surrogate model for visualization and interpretation of complex multi-variate relationships between response variables and environmental drivers. We examine the challenges and opportunities for extracting ecological insights with these interpretation approaches. Specifically, we aim to improve interpretation of ML models by investigating how effectiveness relates to (a) interpretation algorithm, (b) sample size and (c) the presence of spurious explanatory variables.We base the analysis on simulations with known underlying functional relationships between response and predictor variables, with added white noise and the presence of correlated but non-influential variables. The results indicate that deriving ecological insight is strongly affected by interpretation algorithm and spurious variables, and moderately impacted by sample size. Removing spurious variables improves interpretation of ML models. Meanwhile, increasing sample size has limited value in the presence of spurious variables, but increasing sample size does improves performance once spurious variables are omitted. Among the four ranking methods, SI is slightly more effective than the other methods in the presence of spurious variables, while GI and SI yield higher accuracy when spurious variables are removed. PDP is more effective in retrieving underlying functional relationships than ALE, but its reliability declines sharply in the presence of spurious variables. Visualization and interpretation of the interactive effects of predictors and the response variable can be enhanced using surrogate models, including three-dimensional visualizations and use of loess planes to represent independent variable effects and interactions.Machine learning analysts should be aware that including correlated independent variables in ML models with no clear causal relationship to response variables can interfere with ecological inference. When ecological inference is important, ML models should be constructed with independent variables that have clear causal effects on response variables. While interpreting ML models for ecological inference remains challenging, we show that careful choice of interpretation methods, exclusion of spurious variables and adequate sample size can provide more and better opportunities to 'learn from machine learning'.

Woody-biomass projections and drivers of change in sub-Saharan Africa.

Africa's ecosystems have an important role in global carbon dynamics, yet consensus is lacking regarding the amount of carbon stored in woody vegetation and the potential impacts to carbon storage in response to changes in climate, land use, and other Anthropocene risks. Here, we explore the socio-environmental conditions that shaped the contemporary distribution of woody vegetation across sub-Saharan Africa and evaluate ecosystem response to multiple scenarios of climate change, anthropogenic pressures, and fire disturbance. Our projections suggest climate change will have a small but negative effect on above ground woody biomass at the continental scale, and the compounding effects of population growth, increasing human pressures, and socio-climatic driven changes in fire behavior further exacerbate climate-driven trends. Relatively modest continental-scale trends obscure much larger regional perturbations, with climatic and anthropogenic factors leading to increased carbon storage potential in East Africa, offset by large deficits in West, Central, and Southern Africa.

Author Correction: HYSOGs250m, global gridded hydrologic soil groups for curve-number-based runoff modeling.

The original version of this Data Descriptor incorrectly referenced the "United Nations (UN) Food and Agriculture Organization (FAO) soilGrids250m system". This has been corrected to "SoilGrids predictions" throughout the text in both the HTML and PDF versions.

HYSOGs250m, global gridded hydrologic soil groups for curve-number-based runoff modeling.

Hydrologic soil groups (HSGs) are a fundamental component of the USDA curve-number (CN) method for estimation of rainfall runoff; yet these data are not readily available in a format or spatial-resolution suitable for regional- and global-scale modeling applications. We developed a globally consistent, gridded dataset defining HSGs from soil texture, bedrock depth, and groundwater. The resulting data product-HYSOGs250m-represents runoff potential at 250 m spatial resolution. Our analysis indicates that the global distribution of soil is dominated by moderately high runoff potential, followed by moderately low, high, and low runoff potential. Low runoff potential, sandy soils are found primarily in parts of the Sahara and Arabian Deserts. High runoff potential soils occur predominantly within tropical and sub-tropical regions. No clear pattern could be discerned for moderately low runoff potential soils, as they occur in arid and humid environments and at both high and low elevations. Potential applications of this data include CN-based runoff modeling, flood risk assessment, and as a covariate for biogeographical analysis of vegetation distributions.

On regreening and degradation in Sahelian watersheds.

Over many decades our understanding of the impacts of intermittent drought in water-limited environments like the West African Sahel has been influenced by a narrative of overgrazing and human-induced desertification. The desertification narrative has persisted in both scientific and popular conception, such that recent regional-scale recovery ("regreening") and local success stories (community-led conservation efforts) in the Sahel, following the severe droughts of the 1970s-1980s, are sometimes ignored. Here we report a study of watershed-scale vegetation dynamics in 260 watersheds, sampled in four regions of Senegal, Mali, and Niger from 1983-2012, using satellite-derived vegetation indices as a proxy for net primary production. In response to earlier controversy, we first examine the shape of the rainfall-net primary production relationship and how it impacts conclusions regarding greening or degradation. We conclude that the choice of functional relationship has little quantitative impact on our ability to infer greening or degradation trends. We then present an approach to analyze changes in long-term (decade-scale) average rain-use efficiency (an indicator of slowly responding vegetation structural changes) relative to changes in interannual-scale rainfall sensitivity (an indicator of landscape ability to respond rapidly to rainfall variability) to infer trends in greening/degradation of the watersheds in our sample regions. The predominance of increasing rain-use efficiency in our data supports earlier reports of a "greening" trend across the Sahel. However, there are strong regional differences in the extent and direction of change, and in the apparent role of changing woody and herbaceous components in driving those temporal trends.

Analysis of stable states in global savannas: is the CART pulling the horse?

Multiple stable states, bifurcations and thresholds are fashionable concepts in the ecological literature, a recognition that complex ecosystems may at times exhibit the interesting dynamic behaviours predicted by relatively simple biomathematical models. Recently, several papers in Global Ecology and Biogeography, Proceedings of the National Academy of Sciences USA, Science and elsewhere have attempted to quantify the prevalence of alternate stable states in the savannas of Africa, Australia and South America, and the tundra-taiga-grassland transitions of the circum-boreal region using satellite-derived woody canopy cover. While we agree with the logic that basins of attraction can be inferred from the relative frequencies of ecosystem states observed in space and time, we caution that the statistical methodologies underlying the satellite product used in these studies may confound our ability to infer the presence of multiple stable states. We demonstrate this point using a uniformly distributed 'pseudo-tree cover' database for Africa that we use to retrace the steps involved in creation of the satellite tree-cover product and subsequent analysis. We show how classification and regression tree (CART)-based products may impose discontinuities in satellite tree-cover estimates even when such discontinuities are not present in reality. As regional and global remote sensing and geospatial data become more easily accessible for ecological studies, we recommend careful consideration of how error distributions in remote sensing products may interact with the data needs and theoretical expectations of the ecological process under study.