Search for: All records

Universities have been expanding undergraduate data science programs. Involving graduate students in these new opportunities can foster their growth as data science educators. We describe two programs that employ a near-peer mentoring structure, in which graduate students mentor undergraduates, to (a) strengthen their teaching and mentoring skills and (b) provide research and learning experiences for undergraduates from diverse backgrounds. In the Data Science for Social Good program, undergraduate participants work in teams to tackle a data science project with social impact. Graduate mentors guide project work and provide just-in-time teaching and feedback. The Stanford Mentoring in Data Science course offers training in effective and inclusive mentorship strategies. In an experiential learning framework, enrolled graduate students are paired with undergraduate students from non-R1 schools, whom they mentor through weekly one-on-one remote meetings. In end-of-program surveys, mentors reported growth through both programs. Drawing from these experiences, we developed a self-paced mentor training guide, which engages teaching, mentoring and project management abilities. These initiatives and the shared materials can serve as prototypes of future programs that cultivate mutual growth of both undergraduate and graduate students in a high-touch, inclusive, and encouraging environment. 

Drought is one of the most destructive and expensive natural disasters, severely impacting natural resources and risks by depleting water resources and diminishing agricultural yields. Under climate change, accurately predicting drought is critical for mitigating drought-induced risks. However, the intricate interplay among the physical and biological drivers that regulate droughts limits the predictability and understanding of drought, particularly at a subseasonal to seasonal (S2S) time scale. While deep learning has demonstrated the potential to address climate forecasting challenges, its application to drought prediction has received relatively less attention. In this work, we propose a new dataset, DroughtSet, which integrates relevant predictive features and three drought indices from multiple remote sensing and reanalysis datasets across the contiguous United States (CONUS). DroughtSet specifically provides the machine learning community with a new real-world dataset to benchmark drought prediction models and more generally, time-series forecasting methods. Furthermore, we propose a spatial-temporal model SPDrought to predict and interpret S2S droughts. Our model learns from the spatial and temporal information of physical and biological features to predict three types of droughts simultaneously. Multiple strategies are employed to quantify the importance of physical and biological features for drought prediction. Our results provide insights for researchers to better understand the predictability and sensitivity of drought to biological and physical conditions. We aim to contribute to the climate field by proposing a new tool to predict and understand the occurrence of droughts and provide the AI community with a new benchmark to study deep learning applications in climate science. 

Coarse-grained models describe the macroscopic mean response of a process at large scales, which derives from stochastic processes at small scales. Common examples include accounting for velocity fluctuations in a turbulent fluid flow model and cloud evolution in climate models. Most existing techniques for constructing coarse-grained models feature ill-defined parameters whose values are arbitrarily chosen (e.g., a window size), are narrow in their applicability (e.g., only applicable to time series or spatial data), or cannot readily incorporate physics information. Here, we introduce the concept of physics-guided Gaussian process regression as a machine-learning-based coarse-graining technique that is broadly applicable and amenable to input from known physics-based relationships. Using a pair of case studies derived from molecular dynamics simulations, we demonstrate the attractive properties and superior performance of physics-guided Gaussian processes for coarse-graining relative to prevalent benchmarks. The key advantage of Gaussian-process-based coarse-graining is its ability to seamlessly integrate data-driven and physics-based information. 

Plastic debris, including nano-plastic particles (NPPs), has emerged as an important global environmental issue due to its detrimental effects on human health, ecosystems, and climate. Atmospheric processes play an important role in the transportation and fate of plastic particles in the environment. In this study, a high-resolution time-of-flight aerosol mass spectrometer (HR-ToF-AMS) was employed to establish the first online approach for identification and quantification of airborne submicron polystyrene (PS) NPPs from both laboratory-generated and ambient aerosols. The fragmentation ion C8H8+ is identified as the major tracer ion for PS nanoplastic particles, achieving a one-hour detection limit being 4.96 ng/m3. Ambient PS NPPs measured at an urban location in Texas are quantified to be 30 ± 20 ng/m3 by applying the AMS data with a constrained positive matrix factorization (PMF) method using the multilinear engine (ME-2). Careful analysis of ambient data reveals that atmospheric PS NPPs were enhanced as air masses passed through a waste incinerator plant, suggesting incineration of waste may serve as a source of ambient NPPs. The online quantification of NPPs achieved through this study can significantly improves understandings of the source, transport, fate, and climate effects of atmospheric NPPs to mitigate this emerging global environmental issue. 

Abstract Nutrient exchange forms the basis of the ancient symbiotic relationship that occurs between most land plants and arbuscular mycorrhizal (AM) fungi. Plants provide carbon (C) to AM fungi and fungi provide the plant with nutrients such as nitrogen (N) and phosphorous (P). Nutrient addition can alter this symbiotic coupling in key ways, such as reducing AM fungal root colonization and changing the AM fungal community composition. However, environmental parameters that differentiate ecosystems and drive plant distribution patterns (e.g., pH, moisture), are also known to impact AM fungal communities. Identifying the relative contribution of environmental factors impacting AM fungal distribution patterns is important for predicting biogeochemical cycling patterns and plant‐microbe relationships across ecosystems. To evaluate the relative impacts of local environmental conditions and long‐term nutrient addition on AM fungal abundance and composition across grasslands, we studied experimental plots amended for 10 years with N, P, or N and P fertilizer in different grassland ecosystem types, including tallgrass prairie, montane, shortgrass prairie, and desert grasslands. Contrary to our hypothesis, we found ecosystem type, not nutrient treatment, was the main driver of AM fungal root colonization, diversity, and community composition, even when accounting for site‐specific nutrient limitations. We identified several important environmental drivers of grassland ecosystem AM fungal distribution patterns, including aridity, mean annual temperature, root moisture, and soil pH. This work provides empirical evidence for niche partitioning strategies of AM fungal functional guilds and emphasizes the importance of long‐term, large scale research projects to provide ecologically relevant context to nutrient addition studies.