Machine learning for the physics of climate
Related Articles
Predictive learning as the basis of the testing effect
A prominent learning phenomenon is the testing effect, meaning that testing enhances retention more than studying. Emergent frameworks propose fundamental (Hebbian and predictive) learning principles as its basis. Predictive learning posits that learning occurs based on the contrast (error) between a prediction and the feedback on that prediction (prediction error). Here, we propose that in testing (but not studying) scenarios, participants predict potential answers, and its contrast with the subsequent feedback yields a prediction error, which facilitates testing-based learning. To investigate this, we developed an associative memory network incorporating Hebbian and/or predictive learning, together with an experimental design where human participants studied or tested English-Swahili word pairs followed by recognition. Three behavioral experiments (N = 80, 81, 62) showed robust testing effects when feedback was provided. Model fitting (of 10 different models) suggested that only models incorporating predictive learning can account for the breadth of data associated with the testing effect. Our data and model suggest that predictive learning underlies the testing effect.
Understanding learning through uncertainty and bias
Learning allows humans and other animals to make predictions about the environment that facilitate adaptive behavior. Casting learning as predictive inference can shed light on normative cognitive mechanisms that improve predictions under uncertainty. Drawing on normative learning models, we illustrate how learning should be adjusted to different sources of uncertainty, including perceptual uncertainty, risk, and uncertainty due to environmental changes. Such models explain many hallmarks of human learning in terms of specific statistical considerations that come into play when updating predictions under uncertainty. However, humans also display systematic learning biases that deviate from normative models, as studied in computational psychiatry. Some biases can be explained as normative inference conditioned on inaccurate prior assumptions about the environment, while others reflect approximations to Bayesian inference aimed at reducing cognitive demands. These biases offer insights into cognitive mechanisms underlying learning and how they might go awry in psychiatric illness.
Machine learning empowered coherent Raman imaging and analysis for biomedical applications
In situ and in vivo visualization and analysis of functional, endogenous biomolecules in living systems have generated a pivotal impact in our comprehension of biology and medicine. An increasingly adopted approach involves the utilization of molecular vibrational spectroscopy, which delivers notable advantages such as label-free imaging, high spectral density, high sensitivity, and molecule specificity. Nonetheless, analyzing and processing the intricate, multi-dimensional imaging data to extract interpretable and actionable information poses a fundamental obstacle. In contrast to conventional multivariate methods, machine learning has recently gained considerable attention for its capability of discerning essential features from massive datasets. Here, we present a comprehensive review of the latest advancements in the application of machine learning in the molecular spectroscopic imaging fields. We also discuss notable attributes of spectroscopic imaging modalities and explore their broader impact on other imaging techniques.
Event triggers and opinion leaders shape climate change discourse on Weibo
Understanding how real-world events and opinion leaders shape climate change discussions is vital for improving communication and policy formulation to meet global carbon mitigation goals. This study analyzed 5.3 million original posts from Weibo (2012–2022), China’s largest social media platform, to examine climate change discourse. We found five event types triggering 48 discussion peaks, including online activities, international conferences, extreme weather, domestic policies, and international news. Posts generally conveyed positive attitudes, though sentiment decreased during haze pollution and the COVID-19 pandemic. Network analysis revealed seven opinion leader groups with distinct strategies: official media and institutions emphasized political will, global initiatives, and socio-economic implications, while universities and grassroots individuals focused on scientific reality and personal actions. Celebrities and unofficial accounts often highlighted geopolitical topics, especially China-US relations. We suggest reducing fragmented echo chambers and fostering personal connections through digital media platforms to enhance public awareness.
Climate change threatens crop diversity at low latitudes
Climate change alters the climatic suitability of croplands, likely shifting the spatial distribution and diversity of global food crop production. Analyses of future potential food crop diversity have been limited to a small number of crops. Here we project geographical shifts in the climatic niches of 30 major food crops under 1.5–4 °C global warming and assess their impact on current crop production and potential food crop diversity across global croplands. We found that in low-latitude regions, 10–31% of current production would shift outside the climatic niche even under 2 °C global warming, increasing to 20–48% under 3 °C warming. Concurrently, potential food crop diversity would decline on 52% (+2 °C) and 56% (+3 °C) of global cropland. However, potential diversity would increase in mid to high latitudes, offering opportunities for climate change adaptation. These results highlight substantial latitudinal differences in the adaptation potential and vulnerability of the global food system under global warming.
Responses