More Like this

1. Mars, Minecraft, and AI: A Deep Learning Approach to Improve Learning by Building

   https://doi.org/10.1007/978-3-031-64299-9_39  

   Hum, Samuel; Shipley, Evan; Gadbury, Matt; Lane, H Chad; Ginger, Jeffrey (January 2024, Springer Nature Switzerland)

   Olney, A; Chounta, I; Liu, Z; Santos, O (Ed.)

   Middle school students learned about astronomy and STEM concepts while exploring Minecraft simulations of hypothetical Earths and exoplanets. Small groups (n = 24) were tasked with building feasible habitats on Mars. In this paper, we present a scoring scheme for habitat assessment that was used to build novel multi/mixed-input AI models. Using Spearman’s rank correlations, we found that our scoring scheme was reliable with regards to team size and face-to-face instruction time and validated with self-explanation scores. We took an exploratory approach to analyzing image and block data to compare seven different input conditions. Using one-way ANOVAs, we found that the means of the conditions were not equal for accuracy, precision, recall, and F1 metrics. A post hoc Tukey HSD test found that models built using images only were statistically significantly worse than conditions that used block data on the metrics. We also report the results of optimized models using block only data on additional Mars bases (n = 57). 

   more » « less
2. Crash Prediction Using Deep Learning in a Disorienting Spaceflight Analog Balancing Task

   https://doi.org/10.3389/fphys.2022.806357  

   Wang, Yonglin; Tang, Jie; Vimal, Vivekanand Pandey; Lackner, James R.; DiZio, Paul; Hong, Pengyu (January 2022, Frontiers in Physiology)

   Were astronauts forced to land on the surface of Mars using manual control of their vehicle, they would not have familiar gravitational cues because Mars’ gravity is only 0.38 g. They could become susceptible to spatial disorientation, potentially causing mission ending crashes. In our earlier studies, we secured blindfolded participants into a Multi-Axis Rotation System (MARS) device that was programmed to behave like an inverted pendulum. Participants used a joystick to stabilize around the balance point. We created a spaceflight analog condition by having participants dynamically balance in the horizontal roll plane, where they did not tilt relative to the gravitational vertical and therefore could not use gravitational cues to determine their position. We found 90% of participants in our spaceflight analog condition reported spatial disorientation and all of them showed it in their data. There was a high rate of crashing into boundaries that were set at ± 60 ° from the balance point. Our goal was to see whether we could use deep learning to predict the occurrence of crashes before they happened. We used stacked gated recurrent units (GRU) to predict crash events 800 ms in advance with an AUC (area under the curve) value of 99%. When we prioritized reducing false negatives we found it resulted in more false positives. We found that false negatives occurred when participants made destabilizing joystick deflections that rapidly moved the MARS away from the balance point. These unpredictable destabilizing joystick deflections, which occurred in the duration of time after the input data, are likely a result of spatial disorientation. If our model could work in real time, we calculated that immediate human action would result in the prevention of 80.7% of crashes, however, if we accounted for human reaction times (∼400 ms), only 30.3% of crashes could be prevented, suggesting that one solution could be an AI taking temporary control of the spacecraft during these moments. 

   more » « less
3. Nitrogen fixation (acetylene reduction) and denitrification (acetylene block) data from streams across ecoclimatic domains in the United States, 2017-2019

   https://doi.org/10.6073/pasta/df3c065e8339bc28ad9c64d1a1b4c10b  

   Marcarelli, Amy M; Eberhard, Erin K; Kelly, Michelle Catherine; Nevorski, Kevin C (January 2024, Environmental Data Initiative)

   We conducted a cross-ecoregion study to test the hypothesis that N-fixation and denitrification would co-occur in streams and rivers across a range of reactive N concentrations. Between 2017 and 2019, we sampled 30 streams in 13 ecoregions, using chambers to quantify N-fixation using acetylene reduction and denitrification using acetylene block. 25 of the study streams were part of the National Ecological Observatory Network or the StreamPULSE network, which provided data on water temperature, light, nutrients, discharge and metabolism. Although N-fixation and denitrification occur under contrasting environmental conditions, we found that they co-occurred in ca. 40% of stream ecosystems surveyed, and microbes capable of carrying out each process were found in all surveyed streams. This dataset includes the chamber data used to calculate nitrogen fixation and denitrification rates, stream substrate information used to scale rates from substrate to whole-reach scale, and a variety of reach-to-landscape scale covariates used to evaluate predictors of rates across the study streams. 

   more » « less
4. The Houston Methodist lung transplant risk model – a validated tool for pre-transplant risk assessment

   https://doi.org/10.1016/j.athoracsur.2019.03.108  

   Chan EY, Nguyen DT (October 2019, The annals of thoracic surgery)

   BACKGROUND: Lung transplantation is the gold standard for a carefully selected patient population with end-stage lung disease. We sought to create a unique risk stratification model using only preoperative recipient data to predict one-year postoperative mortality during our pre-transplant assessment. METHODS: Data of lung transplant recipients at Houston Methodist Hospital (HMH) from 1/2009 to 12/2014 were extracted from the United Network for Organ Sharing (UNOS) database. Patients were randomly divided into development and validation cohorts. Cox proportional-hazards models were conducted. Variables associated with 1-year mortality post-transplant were assigned weights based on the beta coefficients, and risk scores were derived. Patients were stratified into low-, medium- and high-risk categories. Our model was validated using the validation dataset and data from other US transplant centers in the UNOS database RESULTS: We randomized 633 lung recipients from HMH into the development (n=317 patients) and validation cohort (n=316). One-year survival after transplant was significantly different among risk groups: 95% (low-risk), 84% (medium-risk), and 72% (high-risk) (p<0.001) with a C-statistic of 0.74. Patient survival in the validation cohort was also significantly different among risk groups (85%, 77% and 65%, respectively, p<0.001). Validation of the model with the UNOS dataset included 9,920 patients and found 1-year survival to be 91%, 86% and 82%, respectively (p < 0.001). CONCLUSIONS: Using only recipient data collected at the time of pre-listing evaluation, our simple scoring system has good discrimination power and can be a practical tool in the assessment and selection of potential lung transplant recipients. 

   more » « less
5. Improving Manning's n in Flood Models Using 3D Point Clouds, Flume Experiments, and Deep Learning

   https://doi.org/10.1029/2024WR037665  

   Haces‐Garcia, Francisco; Kotzamanis, Vasileios; Glennie, Craig L; Rifai, Hanadi S (March 2025, Water Resources Research)

   Abstract Friction is one of the cruxes of hydrodynamic modeling; flood conditions are highly sensitive to the Friction Factors (FFs) used to calculate momentum losses. However, empirical FFs are challenging to derive, causing flood models to rely on surrogate observations (such as land cover) and introducing uncertainty. This research presents a laboratory‐trained Deep Neural Network (DNN), developed using flume experiments, to estimateManning's nbased on Point Cloud (PC) data. The DNN was deployed on real‐world lidar PCs to directly estimateManning's nunder regulatory and extreme storm events, showing improved modeling capabilities in both 1D and 2D hydrodynamic models. For 1D models, the lidar estimates decreased differences with values assigned by experts through engineering judgment. For 1D/2D coupled models, the lidar values produced better agreement with flood extents obtained from airborne imagery, while better matching flood insurance claim data for Hurricane Harvey. In both 1D and 1D/2D coupled models, lidar resulted in better agreement with validation gauges. For these reasons, the lidar values ofManning's nwere found to improve both regulatory models and forecasts for extreme storm events, while simultaneously providing a pathway to standardize the estimation of FFs. Changing from land cover to lidar estimates significantly affected fluvial and pluvial flood models, while surge flooding was generally unaffected. Downstream flow conditions were found to change the impacts of FFs to fluvial models. This manuscript introduces a reliable, repeatable, and readily accessible avenue for high‐resolution friction estimation based on 3D PCs, improving flood prediction, and removing uncertainty from hydrodynamic modeling. 

   more » « less