Search for: All records

Recent advances in computer vision for space exploration have handled prediction uncertainties well by approximating multimodal output distribution rather than averaging the distribution. While those advanced multimodal deep learning models could enhance the scientific and engineering value of autonomous systems by making the optimal decisions in uncertain environments, sequential learning of those approximated information has depended on unimodal or bimodal probability distribution. In a sequence of information learning and transfer decisions, the traditional reinforcement learning cannot accommodate the noise in the data that could be useful for gaining information from other locations, thus cannot handle multimodal and multivariate gains in their transition function. Still, there is a lack of interest in learning and transferring multimodal space information effectively to maximally remove the uncertainty. In this study, a new information theory overcomes the traditional entropy approach by actively sensing and learning information in a sequence. Particularly, the autonomous navigation of a team of heterogeneous unmanned ground and aerial vehicle systems in Mars outperforms benchmarks through indirect learning. 

We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another. We approximate the posterior by sequentially removing additional uncertainties across different variables and time, based on data-physics driven correlation, to address a broader class of challenging time-dependent decision-making problems under uncertainty. Extensive experiments on real-world datasets ( i.e., urban traffic data and hurricane ensemble forecasting data) demonstrate the superior performance of the proposed targeted decision-making over the state-of-the-art baseline prediction methods across various settings. 

Abstract Vertical velocities and microphysical processes within deep convection are intricately linked, having wide-ranging impacts on water and mass vertical transport, severe weather, extreme precipitation, and the global circulation. The goal of this research is to investigate the functional form of the relationship between vertical velocity (w) and microphysical processes that convert water vapor into condensed water (M) in deep convection. We examine an ensemble of high-resolution simulations spanning a range of tropical and midlatitude environments, a variety of convective organizational modes, and different model platforms and microphysics schemes. The results demonstrate that the relationship betweenwandMis robustly linear, with the slope of the linear fit being primarily a function of temperature and secondarily a function of supersaturation. TheR²of the linear fit is generally above 0.6 except near the freezing and homogeneous freezing levels. The linear fit is examined both as a function of local in-cloud temperature and environmental temperature. The results for in-cloud temperature are more consistent across the simulation suite, although environmental temperatures are more useful when considering potential observational applications. The linear relationship betweenwandMis substituted into the condensate tendency equation and rearranged to form a diagnostic equation forw. The performance of the diagnostic equation is tested in several simulations, and it is found to diagnose the storm-scale updraft speeds to within 1 m s⁻¹throughout the upper half of the clouds. Potential applications of the linear relationship betweenwandMand the diagnosticwequation are discussed. 

Abstract In the atmosphere,microphysicsrefers to the microscale processes that affect cloud and precipitation particles and is a key linkage among the various components of Earth's atmospheric water and energy cycles. The representation of microphysical processes in models continues to pose a major challenge leading to uncertainty in numerical weather forecasts and climate simulations. In this paper, the problem of treating microphysics in models is divided into two parts: (i) how to represent the population of cloud and precipitation particles, given the impossibility of simulating all particles individually within a cloud, and (ii) uncertainties in the microphysical process rates owing to fundamental gaps in knowledge of cloud physics. The recently developed Lagrangian particle‐based method is advocated as a way to address several conceptual and practical challenges of representing particle populations using traditional bulk and bin microphysics parameterization schemes. For addressing critical gaps in cloud physics knowledge, sustained investment for observational advances from laboratory experiments, new probe development, and next‐generation instruments in space is needed. Greater emphasis on laboratory work, which has apparently declined over the past several decades relative to other areas of cloud physics research, is argued to be an essential ingredient for improving process‐level understanding. More systematic use of natural cloud and precipitation observations to constrain microphysics schemes is also advocated. Because it is generally difficult to quantify individual microphysical process rates from these observations directly, this presents an inverse problem that can be viewed from the standpoint of Bayesian statistics. Following this idea, a probabilistic framework is proposed that combines elements from statistical and physical modeling. Besides providing rigorous constraint of schemes, there is an added benefit of quantifying uncertainty systematically. Finally, a broader hierarchical approach is proposed to accelerate improvements in microphysics schemes, leveraging the advances described in this paper related to process modeling (using Lagrangian particle‐based schemes), laboratory experimentation, cloud and precipitation observations, and statistical methods.