Physical Sciences and Mathematics Commons^™

Integrating Deep Learning And Hydrodynamic Modeling To Improve The Great Lakes Forecast, Pengfei Xue, Aditya Wagh, Gangfeng Ma, Yilin Wang, Yongchao Yang, Tao Liu, Chenfu Huang

Michigan Tech Publications

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, …

Emissions, Shawn Urbanski, Susan O'Neill, Amara L. Holder, Sarah Green, Rick L. Graw

Michigan Tech Publications

This chapter assesses the current state of the science regarding the composition, intensity, and drivers of wildland fire emissions in the USA and Canada. Globally and in the USA wildland fires are a major source of gases and aerosols which have significant air quality impacts and climate interactions. Wildland fire smoke can trigger severe pollution episodes with substantial effects on public health. Fire emissions can degrade air quality at considerable distances downwind, hampering efforts by air regulators to meet air standards. Fires are a major global source of aerosols which affect the climate system by absorbing and scattering radiation and …

Hb-Pls: A Statistical Method For Identifying Biological Process Or Pathway Regulators By Integrating Huber Loss And Berhu Penalty With Partial Least Squares Regression, Wenping Deng, Kui Zhang, Cheng He, Sanzhen Liu, Hairong Wei

Michigan Tech Publications

Gene expression data features high dimensionality, multicollinearity, and non-Gaussian distribution noise, posing hurdles for identification of true regulatory genes controlling a biological process or pathway. In this study, we integrated the Huber loss function and the Berhu penalty (HB) into partial least squares (PLS) framework to deal with the high dimension and multicollinearity property of gene expression data, and developed a new method called HB-PLS regression to model the relationships between regulatory genes and pathway genes. To solve the Huber-Berhu optimization problem, an accelerated proximal gradient descent algorithm with at least 10 times faster than the general convex optimization solver …

Insights On Dissolved Organic Matter Production Revealed By Removal Of Charge-Transfer Interactions In Senescent Leaf Leachates, Karl M. Meingast, Brice K. Grunert, Sarah A. Green, Evan S. Kane, Nastaran Khademimoshgenani

Michigan Tech Publications

Dissolved organic matter (DOM) is a critical part of the global carbon cycle. Currently, it is understood that at least a portion of the chromophoric DOM (CDOM) character can be described through an electronic interaction of charge transfer (CT) complexes. While much work has been done to understand the influence of CT on soil and aquatic reference standard DOM, little is known about the influence of CT in fresh terrestrially derived DOM. In this study, leaf litter leachates from three tree species were treated (reduced) with sodium borohydride to determine the contribution of CT on a source of fresh terrestrial …

Tgmi: An Efficient Algorithm For Identifying Pathway Regulators Through Evaluation Of Triple-Gene Mutual Interaction, Chathura J. Gunasekara, Kui Zhang, Wenping Deng, Laura E. Brown, Hairong Wei

Michigan Tech Publications

Despite their important roles, the regulators for most metabolic pathways and biological processes remain elusive. Presently, the methods for identifying metabolic pathway and biological process regulators are intensively sought after. We developed a novel algorithm called triple-gene mutual interaction (TGMI) for identifying these regulators using high-throughput gene expression data. It first calculated the regulatory interactions among triple gene blocks (two pathway genes and one transcription factor (TF)), using conditional mutual information, and then identifies significantly interacted triple genes using a newly identified novel mutual interaction measure (MIM), which was substantiated to reflect strengths of regulatory interactions within each triple gene …

Growth Performance, Organ-Level Ionic Relations And Organic Osmoregulation Of Elaeagnus Angustifolia In Response To Salt Stress, Zhengxiang Liu, Jiangfeng Zhu, Xiuyan Yang, Haiwen Wu, Qi Wei, Hairong Wei, Huaxin Zhang

Michigan Tech Publications

Elaeagnus angustifolia is one of the most extensively afforested tree species in environment-harsh regions of northern China. Despite its exceptional tolerance to saline soil, the intrinsic adaptive physiology has not been revealed. In this study, we investigated the growth, organ-level ionic relations and organic osmoregulation of the seedlings hydroponically treated with 0, 100 and 200 mM NaCl for 30 days. We found that the growth characteristics and the whole-plant dry weight were not obviously stunted, but instead, were even slightly stimulated by the treatment of 100 mM NaCl. In contrast, these traits were significantly inhibited by 200 mM NaCl treatment. …

The Effect Of Poplar Psngs1.2 Overexpression On Growth, Secondary Cell Wall, And Fiber Characteristics In Tobacco, Tingting Lu, Lulu Liu, Minjing Wei, Yingying Liu, Zianshang Qu, Chuanping Yang, Hairong Wei, Zhigang Wei

Michigan Tech Publications

The glutamine synthetase (GS1) is a key enzyme that catalyzes the reaction of glutamate and ammonia to produce glutamine in the nitrogen (N) metabolism. Previous studies on GS1s in several plant species suggest that overexpression of GS1s can enhance N utilization, accelerate plant vegetative growth, and change wood formation. In this study, we isolated a GS1 gene, termed PsnGS1.2, from Populus simonii × Populus nigra. This gene was expressed at a higher level in roots, and relatively lower but detectable levels in xylem, leaves and phloem of P. simonii × P. nigra. The protein encoded by PsnGS1.2 is …

Bottom-Up Ggm Algorithm For Constructing Multilayered Hierarchical Gene Regulatory Networks That Govern Biological Pathways Or Processes, Sapna Kupari, Wenping Deng, Chathura J. Gunasekara, Vincent Chiang, Huann-Sheng Chen, Hairong Wei, Et. Al.

Michigan Tech Publications

Background: Multilayered hierarchical gene regulatory networks (ML-hGRNs) are very important for understanding genetics regulation of biological pathways. However, there are currently no computational algorithms available for directly building ML-hGRNs that regulate biological pathways.

Results: A bottom-up graphic Gaussian model (GGM) algorithm was developed for constructing ML-hGRN operating above a biological pathway using small- to medium-sized microarray or RNA-seq data sets. The algorithm first placed genes of a pathway at the bottom layer and began to construct an ML-hGRN by evaluating all combined triple genes: two pathway genes and one regulatory gene. The algorithm retained all triple genes where a regulatory …

Shifting Environmental Controls On Ch4 Fluxes In A Sub-Boreal Peatland, Thomas G. Pypker, P. A. Moore, John A. Hribljan, Rodney Chimner

Michigan Tech Publications

We monitored CO₂ and CH₄ fluxes using eddy covariance from 19 May to 27 September 2011 in a poor fen located in northern Michigan. The objectives of this paper are to: (1) quantify the flux of CH₄ from a sub-boreal peatland, and (2) determine which abiotic and biotic factors were the most correlated to the flux of CH₄ over the measurement period. Net daily CH₄ fluxes increased from 70 mg CH₄ m⁻² d⁻¹ to 220 mg CH₄ m⁻² d⁻¹ from mid May to mid July. After July, CH_{4 …}