More Like this

1. Evaluating a global soil moisture dataset from a multitask model (GSM3 v1.0) with potential applications for crop threats

   https://doi.org/10.5194/gmd-16-1553-2023  

   Liu, Jiangtao; Hughes, David; Rahmani, Farshid; Lawson, Kathryn; Shen, Chaopeng (January 2023, Geoscientific Model Development)

   Abstract. Climate change threatens our ability to grow food for an ever-increasing population. There is aneed for high-quality soil moisture predictions in under-monitored regionslike Africa. However, it is unclear if soil moisture processes are globallysimilar enough to allow our models trained on available in situ data tomaintain accuracy in unmonitored regions. We present a multitask longshort-term memory (LSTM) model that learns simultaneously from globalsatellite-based data and in situ soil moisture data. This model is evaluated inboth random spatial holdout mode and continental holdout mode (trained onsome continents, tested on a different one). The model compared favorably tocurrent land surface models, satellite products, and a candidate machinelearning model, reaching a global median correlation of 0.792 for the randomspatial holdout test. It behaved surprisingly well in Africa and Australia,showing high correlation even when we excluded their sites from the trainingset, but it performed relatively poorly in Alaska where rapid changes areoccurring. In all but one continent (Asia), the multitask model in theworst-case scenario test performed better than the soil moisture activepassive (SMAP) 9 km product. Factorial analysis has shown that the LSTM model'saccuracy varies with terrain aspect, resulting in lower performance for dryand south-facing slopes or wet and north-facing slopes. This knowledgehelps us apply the model while understanding its limitations. This model isbeing integrated into an operational agricultural assistance applicationwhich currently provides information to 13 million African farmers. 

   more » « less
2. Fluctuating selection and global change: a synthesis and review on disentangling the roles of climate amplitude, predictability and novelty

   https://doi.org/10.1098/rspb.2021.0727  

   Bitter, M. C.; Wong, J. M.; Dam, H. G.; Donelan, S. C.; Kenkel, C. D.; Komoroske, L. M.; Nickols, K. J.; Rivest, E. B.; Salinas, S.; Burgess, S. C.; et al (August 2021, Proceedings of the Royal Society B: Biological Sciences)

   A formidable challenge for global change biologists is to predict how natural populations will respond to the emergence of conditions not observed at present, termed novel climates. Popular approaches to predict population vulnerability are based on the expected degree of novelty relative to the amplitude of historical climate fluctuations experienced by a population. Here, we argue that predictions focused on amplitude may be inaccurate because they ignore the predictability of environmental fluctuations in driving patterns of evolution and responses to climate change. To address this disconnect, we review major findings of evolutionary theory demonstrating the conditions under which phenotypic plasticity is likely to evolve in natural populations, and how plasticity decreases population vulnerability to novel environments. We outline key criteria that experimental studies should aim for to effectively test theoretical predictions, while controlling for the degree of climate novelty. We show that such targeted tests of evolutionary theory are rare, with marine systems being overall underrepresented in this venture despite exhibiting unique opportunities to test theory. We conclude that with more robust experimental designs that manipulate both the amplitude and predictability of fluctuations, while controlling for the degree of novelty, we may better predict population vulnerability to climate change. 

   more » « less
3. Plasticity’s role in adaptive evolution depends on environmental change components

   https://doi.org/10.1016/j.tree.2022.08.008  

   Vinton, Anna C.; Gascoigne, Samuel J.L.; Sepil, Irem; Salguero-Gómez, Roberto (December 2022, Trends in Ecology & Evolution)

   Dr Andrea E. A. Stephens (Ed.)

   To forecast extinction risks of natural populations under climate change and direct human impacts, an integrative understanding of both phenotypic plasticity and adaptive evolution is essential. To date, the evidence for whether, when, and how much plasticity facilitates adaptive responses in changing environments is contradictory. We argue that explicitly considering three key environmental change components – rate of change, variance, and temporal autocorrelation – affords a unifying framework of the impact of plasticity on adaptive evolution. These environmental components each distinctively effect evolutionary and ecological processes underpinning population viability. Using this framework, we develop expectations regarding the interplay between plasticity and adaptive evolution in natural populations. This framework has the potential to improve predictions of population viability in a changing world. 

   more » « less
4. A Cautionary Note Regarding the Consequences of Balancing for Fair Comparisons in Population Ecology

   https://doi.org/10.1002/1438-390x.70016  

   Hernández, Christina M; Koons, David N; Salguero‐Gómez, Roberto (April 2026, Population Ecology)

   ABSTRACT Population ecology has amassed a significant volume of demographic data across the Tree of Life. Together, these data enable comparative analyses at unprecedented taxonomic and biogeographic scales to examine patterns of demographic performance and their mechanisms. However, macroecological analysis of heterogeneous data and models from diverse study systems comes with risks, and care must be taken to ensure that the patterns from comparative approaches are biologically meaningful, rather than driven by model‐specific artifacts. Recently, a balancing approach has been proposed as a solution to “distorted” population structure, particularly for evaluating transient (short‐term) population dynamics. We argue that some distortion is the result of true biological processes, and that balancing over‐corrects for distortion due to census timing (pre‐ vs. post‐breeding). We lay out the relationship between demographic census design and the issues purported to be solved by balancing. Using a large dataset of carefully‐selected matrix population models from plants and animals, we demonstrate that balancing changes biological interpretation of the relationship between reproductive traits and demographic resilience. We also highlight how application of balancing outside of its narrow original application to transient metrics can be problematic. We argue that meaningful comparisons require tailored approaches that respect the structure and context of demographic data. A more nuanced strategy–based on the biological realities of life cycles, census design, and reproductive strategies–will improve the robustness and interpretation of comparative demographic analyses. 

   more » « less
5. Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST)

   Hickey, Jimmy; Williams, Jonathan P; Hector, Emily C (November 2024, Journal of machine learning research)

   Transfer learning uses a data model, trained to make predictions or inferences on data from one population, to make reliable predictions or inferences on data from another population. Most existing transfer learning approaches are based on fine-tuning pre-trained neural network models, and fail to provide crucial uncertainty quantification. We develop a statistical framework for model predictions based on transfer learning, called RECaST. The primary mechanism is a Cauchy random effect that recalibrates a source model to a target population; we mathematically and empirically demonstrate the validity of our RECaST approach for transfer learning between linear models, in the sense that prediction sets will achieve their nominal stated coverage, and we numerically illustrate the method's robustness to asymptotic approximations for nonlinear models. Whereas many existing techniques are built on particular source models, RECaST is agnostic to the choice of source model, and does not require access to source data. For example, our RECaST transfer learning approach can be applied to a continuous or discrete data model with linear or logistic regression, deep neural network architectures, etc. Furthermore, RECaST provides uncertainty quantification for predictions, which is mostly absent in the literature. We examine our method's performance in a simulation study and in an application to real hospital data. 

   more » « less