Wildfire smoke impacts lake ecosystems.

Wildfire activity is increasing globally. The resulting smoke plumes can travel hundreds to thousands of kilometers, reflecting or scattering sunlight and depositing particles within ecosystems. Several key physical, chemical, and biological processes in lakes are controlled by factors affected by smoke. The spatial and temporal scales of lake exposure to smoke are extensive and under-recognized. We introduce the concept of the lake smoke-day, or the number of days any given lake is exposed to smoke in any given fire season, and quantify the total lake smoke-day exposure in North America from 2019 to 2021. Because smoke can be transported at continental to intercontinental scales, even regions that may not typically experience direct burning of landscapes by wildfire are at risk of smoke exposure. We found that 99.3% of North America was covered by smoke, affecting a total of 1,333,687 lakes ≥10 ha. An incredible 98.9% of lakes experienced at least 10 smoke-days a year, with 89.6% of lakes receiving over 30 lake smoke-days, and lakes in some regions experiencing up to 4 months of cumulative smoke-days. Herein we review the mechanisms through which smoke and ash can affect lakes by altering the amount and spectral composition of incoming solar radiation and depositing carbon, nutrients, or toxic compounds that could alter chemical conditions and impact biota. We develop a conceptual framework that synthesizes known and theoretical impacts of smoke on lakes to guide future research. Finally, we identify emerging research priorities that can help us better understand how lakes will be affected by smoke as wildfire activity increases due to climate change and other anthropogenic activities.

Transcriptional profiles of non-neuronal and immune cells in mouse trigeminal ganglia.

Non-neuronal cells constitute 90%-95% of sensory ganglia. These cells, especially glial and immune cells, play critical roles in the modulation of sensory neurons. This study aimed to identify, profile, and summarize the types of trigeminal ganglion (TG) non-neuronal cells in naïve male mice using published and our own data generated by single-cell RNA sequencing, flow cytometry, and immunohistochemistry. TG has five types of non-neuronal cells, namely, glial, fibroblasts, smooth muscle, endothelial, and immune cells. There is an agreement among publications for glial, fibroblasts, smooth muscle, and endothelial cells. Based on gene profiles, glial cells were classified as myelinated and non-myelinated Schwann cells and satellite glial cells. Mpz has dominant expression in Schwann cells, and Fabp7 is specific for SCG. Two types of Col1a2+ fibroblasts located throughout TG were distinguished. TG smooth muscle and endothelial cells in the blood vessels were detected using well-defined markers. Our study reported three types of macrophages (Mph) and four types of neutrophils (Neu) in TG. Mph were located in the neuronal bodies and nerve fibers and were sub-grouped by unique transcriptomic profiles with Ccr2, Cx3cr1, and Iba1 as markers. A comparison of databases showed that type 1 Mph is similar to choroid plexus-low (CPlo) border-associated Mph (BAMs). Type 2 Mph has the highest prediction score with CPhi BAMs, while type 3 Mph is distinct. S100a8+ Neu were located in the dura surrounding TG and were sub-grouped by clustering and expressions of Csf3r, Ly6G, Ngp, Elane, and Mpo. Integrative analysis of published datasets indicated that Neu-1, Neu-2, and Neu-3 are similar to the brain Neu-1 group, while Neu-4 has a resemblance to the monocyte-derived cells. Overall, the generated and summarized datasets on non-neuronal TG cells showed a unique composition of myeloid cell types in TG and could provide essential and fundamental information for studies on cell plasticity, interactomic networks between neurons and non-neuronal cells, and function during a variety of pain conditions in the head and neck regions.

Estimation of tomato water status with photochemical reflectance index and machine learning: Assessment from proximal sensors and UAV imagery.

Tracking plant water status is a critical step towards the adaptive precision irrigation management of processing tomatoes, one of the most important specialty crops in California. The photochemical reflectance index (PRI) from proximal sensors and the high-resolution unmanned aerial vehicle (UAV) imagery provide an opportunity to monitor the crop water status efficiently. Based on data from an experimental tomato field with intensive aerial and plant-based measurements, we developed random forest machine learning regression models to estimate tomato stem water potential (ψ stem), (using observations from proximal sensors and 12-band UAV imagery, respectively, along with weather data. The proximal sensor-based model estimation agreed well with the plant ψ stem with R 2 of 0.74 and mean absolute error (MAE) of 0.63 bars. The model included PRI, normalized difference vegetation index, vapor pressure deficit, and air temperature and tracked well with the seasonal dynamics of ψ stem across different plots. A separate model, built with multiple vegetation indices (VIs) from UAV imagery and weather variables, had an R 2 of 0.81 and MAE of 0.67 bars. The plant-level ψ stem maps generated from UAV imagery closely represented the water status differences of plots under different irrigation treatments and also tracked well the temporal change among flights. PRI was found to be the most important VI in both the proximal sensor- and the UAV-based models, providing critical information on tomato plant water status. This study demonstrated that machine learning models can accurately estimate the water status by integrating PRI, other VIs, and weather data, and thus facilitate data-driven irrigation management for processing tomatoes.

Tree-level almond yield estimation from high resolution aerial imagery with convolutional neural network.

Introduction: Estimating and understanding the yield variability within an individual field is critical for precision agriculture resource management of high value tree crops. Recent advancements in sensor technologies and machine learning make it possible to monitor orchards at very high spatial resolution and estimate yield at individual tree level. Methods: This study evaluates the potential of utilizing deep learning methods to predict tree-level almond yield with multi-spectral imagery. We focused on an almond orchard with the 'Independence' cultivar in California, where individual tree harvesting and yield monitoring was conducted for ~2,000 trees and summer aerial imagery at 30cm was acquired for four spectral bands in 2021. We developed a Convolutional Neural Network (CNN) model with a spatial attention module to take the multi-spectral reflectance imagery directly for almond fresh weight estimation at the tree level. Results: The deep learning model was shown to predict the tree level yield very well, with a R2 of 0.96 (±0.002) and Normalized Root Mean Square Error (NRMSE) of 6.6% (±0.2%), based on 5-fold cross validation. The CNN estimation captured well the patterns of yield variation between orchard rows, along the transects, and from tree to tree, when compared to the harvest data. The reflectance at the red edge band was found to play the most important role in the CNN yield estimation. Discussion: This study demonstrates the significant improvement of deep learning over traditional linear regression and machine learning methods for accurate and robust tree level yield estimation, highlighting the potential for data-driven site-specific resource management to ensure agriculture sustainability.

Characterizing Macrophages Diversity in COVID-19 Patients Using Deep Learning.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiological agent responsible for coronavirus disease 2019 (COVID-19), has affected the lives of billions and killed millions of infected people. This virus has been demonstrated to have different outcomes among individuals, with some of them presenting a mild infection, while others present severe symptoms or even death. The identification of the molecular states related to the severity of a COVID-19 infection has become of the utmost importance to understanding the differences in critical immune response. In this study, we computationally processed a set of publicly available single-cell RNA-Seq (scRNA-Seq) data of 12 Bronchoalveolar Lavage Fluid (BALF) samples diagnosed as having a mild, severe, or no infection, and generated a high-quality dataset that consists of 63,734 cells, each with 23,916 genes. We extended the cell-type and sub-type composition identification and our analysis showed significant differences in cell-type composition in mild and severe groups compared to the normal. Importantly, inflammatory responses were dramatically elevated in the severe group, which was evidenced by the significant increase in macrophages, from 10.56% in the normal group to 20.97% in the mild group and 34.15% in the severe group. As an indicator of immune defense, populations of T cells accounted for 24.76% in the mild group and decreased to 7.35% in the severe group. To verify these findings, we developed several artificial neural networks (ANNs) and graph convolutional neural network (GCNN) models. We showed that the GCNN models reach a prediction accuracy of the infection of 91.16% using data from subtypes of macrophages. Overall, our study indicates significant differences in the gene expression profiles of inflammatory response and immune cells of severely infected patients.

Transformer for Gene Expression Modeling (T-GEM): An Interpretable Deep Learning Model for Gene Expression-Based Phenotype Predictions.

Deep learning has been applied in precision oncology to address a variety of gene expression-based phenotype predictions. However, gene expression data's unique characteristics challenge the computer vision-inspired design of popular Deep Learning (DL) models such as Convolutional Neural Network (CNN) and ask for the need to develop interpretable DL models tailored for transcriptomics study. To address the current challenges in developing an interpretable DL model for modeling gene expression data, we propose a novel interpretable deep learning architecture called T-GEM, or Transformer for Gene Expression Modeling. We provided the detailed T-GEM model for modeling gene-gene interactions and demonstrated its utility for gene expression-based predictions of cancer-related phenotypes, including cancer type prediction and immune cell type classification. We carefully analyzed the learning mechanism of T-GEM and showed that the first layer has broader attention while higher layers focus more on phenotype-related genes. We also showed that T-GEM's self-attention could capture important biological functions associated with the predicted phenotypes. We further devised a method to extract the regulatory network that T-GEM learns by exploiting the attributions of self-attention weights for classifications and showed that the network hub genes were likely markers for the predicted phenotypes.

Beyond green environments: Multi-scale difference in human exposure to greenspace in China.

Greenspace exposure metrics can allow for comparisons of green space supply across time, space, and population groups, and for inferring patterns of variation in opportunities for people to enjoy the health and recreational benefits of nearby green environments. A better understanding of greenspace exposure differences across various spatial scales is a critical requirement for lessening environmental health disparities. However, existing studies are typically limited to a single city or across selected cities, which severely limits the use of results in measuring systemic national and regional scale differences that might need policy at above individual city planning level. To close this knowledge gap, our study aims to provide a holistic assessment of multi-scale greenspace exposure across provinces, cities, counties, towns, and land parcels for the whole of China. We mapped the nationwide fractional greenspace coverage at 10 m with Sentinel-2 satellite imagery, and then modeled population-weighted greenspace exposure to examine variation of greenspace exposure across scales. Our results show a prominent scaling effect of greenspace exposure across multi-scale administrative divisions in China, suggesting, as expected, an increase in heterogeneity with finer spatial scales. We also identify an asymmetric pattern of the difference between greenspace exposure and greenspace coverage, across a geo-demographic demarcation boundary (i.e., along the Heihe-Tengchong Line). In general, the greenspace coverage rate will overestimate more realistic human exposure to greenspace in East China while underestimating in West China. We further found that, in China, more recently urbanized areas have much better greenspace exposure than older urban areas. Our study provides a spatially explicit greenspace exposure metric for discovering multi-scale greenspace exposure difference, which will enhance governments' capacity to quantify environmental justice, detect vulnerable greenspace exposure risk hotspots, prioritize greenspace management at the supra-city scale, and monitor the balance between greenspace supply and demand.

Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell analyses besides the traditional machine learning approaches. Here, we survey a total of 25 DL algorithms and their applicability for a specific step in the single cell RNA-seq processing pipeline. Specifically, we establish a unified mathematical representation of variational autoencoder, autoencoder, generative adversarial network and supervised DL models, compare the training strategies and loss functions for these models, and relate the loss functions of these models to specific objectives of the data processing step. Such a presentation will allow readers to choose suitable algorithms for their particular objective at each step in the pipeline. We envision that this survey will serve as an important information portal for learning the application of DL for scRNA-seq analysis and inspire innovative uses of DL to address a broader range of new challenges in emerging multi-omics and spatial single-cell sequencing.

Compound Risk of Air Pollution and Heat Days and the Influence of Wildfire by SES across California, 2018-2020: Implications for Environmental Justice in the Context of Climate Change.

Major wildfires and heatwaves have begun to increase in frequency throughout much of the United States, particularly in western states such as California, causing increased risk to public health. Air pollution is exacerbated by both wildfires and warmer temperatures, thus adding to such risk. With climate change and the continued increase in global average temperatures, the frequency of major wildfires, heat days, and unhealthy air pollution episodes is projected to increase, resulting in the potential for compounding risks. Risks will likely vary by region and may disproportionately impact low-income communities and communities of color. In this study, we processed daily particulate matter (PM) data from over 18,000 low-cost PurpleAir sensors, along with gridMET daily maximum temperature data and government-compiled wildfire perimeter data from 2018-2020 in order to examine the occurrence of compound risk (CR) days (characterized by high temperature and high PM2.5) at the census tract level in California, and to understand how such days have been impacted by the occurrence of wildfires. Using American Community Survey data, we also examined the extent to which CR days were correlated with household income, race/ethnicity, education, and other socioeconomic factors at the census tract level. Results showed census tracts with a higher frequency of CR days to have statistically higher rates of poverty and unemployment, along with high proportions of child residents and households without computers. The frequency of CR days and elevated daily PM2.5 concentrations appeared to be strongly related to the occurrence of nearby wildfires, with over 20% of days with sensor-measured average PM2.5 > 35 µg/m3 showing a wildfire within a 100 km radius and over two-thirds of estimated CR days falling on such days with a nearby wildfire. Findings from this study are important to policymakers and government agencies who preside over the allocation of state resources as well as organizations seeking to empower residents and establish climate resilient communities.

Wildfire response to changing daily temperature extremes in California's Sierra Nevada.

Burned area has increased across California, especially in the Sierra Nevada range. Recent fires there have had devasting social, economic, and ecosystem impacts. To understand the consequences of new extremes in fire weather, here we quantify the sensitivity of wildfire occurrence and burned area in the Sierra Nevada to daily meteorological variables during 2001­2020. We find that the likelihood of fire occurrence increases nonlinearly with daily temperature during summer, with a 1°C increase yielding a 19 to 22% increase in risk. Area burned has a similar, nonlinear sensitivity, with 1°C of warming yielding a 22 to 25% increase in risk. Solely considering changes in summer daily temperatures from climate model projections, we estimate that by the 2040s, fire number will increase by 51 ± 32%, and burned area will increase by 59 ± 33%. These trends highlight the threat posed to fire management by hotter and drier summers.

Disproportionate Impacts of Wildfires among Elderly and Low-Income Communities in California from 2000-2020.

Wildfires can be detrimental to urban and rural communities, causing impacts in the form of psychological stress, direct physical injury, and smoke-related morbidity and mortality. This study examined the area burned by wildfires over the entire state of California from the years 2000 to 2020 in order to quantify and identify whether burned area and fire frequency differed across Census tracts according to socioeconomic indicators over time. Wildfire data were obtained from the California Fire and Resource Assessment Program (FRAP) and National Interagency Fire Center (NIFC), while demographic data were obtained from the American Community Survey. Results showed a doubling in the number of Census tracts that experienced major wildfires and a near doubling in the number of people residing in wildfire-impacted Census tracts, mostly due to an over 23,000 acre/year increase in the area burned by wildfires over the last two decades. Census tracts with a higher fire frequency and burned area had lower proportions of minority groups on average. However, when considering Native American populations, a greater proportion resided in highly impacted Census tracts. Such Census tracts also had higher proportions of older residents. In general, high-impact Census tracts tended to have higher proportions of low-income residents and lower proportions of high-income residents, as well as lower median household incomes and home values. These findings are important to policymakers and state agencies as it relates to environmental justice and the allocation of resources before, during, and after wildfires in the state of California.

Drone phenotyping and machine learning enable discovery of loci regulating daily floral opening in lettuce.

Flower opening and closure are traits of reproductive importance in all angiosperms because they determine the success of self- and cross-pollination. The temporal nature of this phenotype rendered it a difficult target for genetic studies. Cultivated and wild lettuce, Lactuca spp., have composite inflorescences that open only once. An L. serriola×L. sativa F6 recombinant inbred line (RIL) population differed markedly for daily floral opening time. This population was used to map the genetic determinants of this trait; the floral opening time of 236 RILs was scored using time-course image series obtained by drone-based phenotyping on two occasions. Floral pixels were identified from the images using a support vector machine with an accuracy >99%. A Bayesian inference method was developed to extract the peak floral opening time for individual genotypes from the time-stamped image data. Two independent quantitative trait loci (QTLs; Daily Floral Opening 2.1 and qDFO8.1) explaining >30% of the phenotypic variation in floral opening time were discovered. Candidate genes with non-synonymous polymorphisms in coding sequences were identified within the QTLs. This study demonstrates the power of combining remote sensing, machine learning, Bayesian statistics, and genome-wide marker data for studying the genetics of recalcitrant phenotypes.

Prediction and interpretation of cancer survival using graph convolution neural networks.

The survival rate of cancer has increased significantly during the past two decades for breast, prostate, testicular, and colon cancer, while the brain and pancreatic cancers have a much lower median survival rate that has not improved much over the last forty years. This has imposed the challenge of finding gene markers for early cancer detection and treatment strategies. Different methods including regression-based Cox-PH, artificial neural networks, and recently deep learning algorithms have been proposed to predict the survival rate for cancers. We established in this work a novel graph convolution neural network (GCNN) approach called Surv_GCNN to predict the survival rate for 13 different cancer types using the TCGA dataset. For each cancer type, 6 Surv_GCNN models with graphs generated by correlation analysis, GeneMania database, and correlation + GeneMania were trained with and without clinical data to predict the risk score (RS). The performance of the 6 Surv_GCNN models was compared with two other existing models, Cox-PH and Cox-nnet. The results showed that Cox-PH has the worst performance among 8 tested models across the 13 cancer types while Surv_GCNN models with clinical data reported the best overall performance, outperforming other competing models in 7 out of 13 cancer types including BLCA, BRCA, COAD, LUSC, SARC, STAD, and UCEC. A novel network-based interpretation of Surv_GCNN was also proposed to identify potential gene markers for breast cancer. The signatures learned by the nodes in the hidden layer of Surv_GCNN were identified and were linked to potential gene markers by network modularization. The identified gene markers for breast cancer have been compared to a total of 213 gene markers from three widely cited lists for breast cancer survival analysis. About 57% of gene markers obtained by Surv_GCNN with correlation + GeneMania graph either overlap or directly interact with the 213 genes, confirming the effectiveness of the identified markers by Surv_GCNN.

Antidepressant-Like Effects of Coumaroylspermidine Extract From Safflower Injection Residues.

In this study, a total coumaroylspermidine extract (CSE), which included four coumaroylspermidine compounds, was prepared from safflower injection (a traditional Chinese medicine) residues for the first time. The total content of the four coumaroylspermidine compounds was determined to be 64.86 ± 0.41% using high-performance liquid chromatography. We then evaluated the anti-depressant effect of CSE by using a chronic unpredictable mild stress (CUMS) model in rats. Results of sucrose preference tests, open field tests, and forced swimming tests suggest that CSE exhibits a significant anti-depressant effect. In studies to explore the mechanism, CSE was found to inhibit the increases in levels of corticosterone and decreases in levels of 5-hydroxytryptamine, dopamine, and noradrenaline induced by CUMS. Metabolic profiling showed that 10 endogenous metabolites and four metabolic pathways were altered after CSE treatment. Thus, this study not only found a spermidine extract with antidepressant effect from safflower injection residue for the first time but also provided a way for the efficient utilize of safflower injection residue.

Advancing Agricultural Production With Machine Learning Analytics: Yield Determinants for California's Almond Orchards.

Agricultural productivity is subject to various stressors, including abiotic and biotic threats, many of which are exacerbated by a changing climate, thereby affecting long-term sustainability. The productivity of tree crops such as almond orchards, is particularly complex. To understand and mitigate these threats requires a collection of multi-layer large data sets, and advanced analytics is also critical to integrate these highly heterogeneous datasets to generate insights about the key constraints on the yields at tree and field scales. Here we used a machine learning approach to investigate the determinants of almond yield variation in California's almond orchards, based on a unique 10-year dataset of field measurements of light interception and almond yield along with meteorological data. We found that overall the maximum almond yield was highly dependent on light interception, e.g., with each one percent increase in light interception resulting in an increase of 57.9 lbs/acre in the potential yield. Light interception was highest for mature sites with higher long term mean spring incoming solar radiation (SRAD), and lowest for younger orchards when March maximum temperature was lower than 19°C. However, at any given level of light interception, actual yield often falls significantly below full yield potential, driven mostly by tree age, temperature profiles in June and winter, summer mean daily maximum vapor pressure deficit (VPDmax), and SRAD. Utilizing a full random forest model, 82% (±1%) of yield variation could be explained when using a sixfold cross validation, with a RMSE of 480 ± 9 lbs/acre. When excluding light interception from the predictors, overall orchard characteristics (such as age, location, and tree density) and inclusive meteorological variables could still explain 78% of yield variation. The model analysis also showed that warmer winter conditions often limited mature orchards from reaching maximum yield potential and summer VPDmax beyond 40 hPa significantly limited the yield. Our findings through the machine learning approach improved our understanding of the complex interaction between climate, canopy light interception, and almond nut production, and demonstrated a relatively robust predictability of almond yield. This will ultimately benefit data-driven climate adaptation and orchard nutrient management approaches.

Classification of Cancer Types Using Graph Convolutional Neural Networks.

BACKGROUND: Cancer has been a leading cause of death in the United States with significant health care costs. Accurate prediction of cancers at an early stage and understanding the genomic mechanisms that drive cancer development are vital to the improvement of treatment outcomes and survival rates, thus resulting in significant social and economic impacts. Attempts have been made to classify cancer types with machine learning techniques during the past two decades and deep learning approaches more recently. RESULTS: In this paper, we established four models with graph convolutional neural network (GCNN) that use unstructured gene expressions as inputs to classify different tumor and non-tumor samples into their designated 33 cancer types or as normal. Four GCNN models based on a co-expression graph, co-expression+singleton graph, protein-protein interaction (PPI) graph, and PPI+singleton graph have been designed and implemented. They were trained and tested on combined 10,340 cancer samples and 731 normal tissue samples from The Cancer Genome Atlas (TCGA) dataset. The established GCNN models achieved excellent prediction accuracies (89.9-94.7%) among 34 classes (33 cancer types and a normal group). In silico gene-perturbation experiments were performed on four models based on co-expression graph, co-expression+singleton, PPI graph, and PPI+singleton graphs. The co-expression GCNN model was further interpreted to identify a total of 428 markers genes that drive the classification of 33 cancer types and normal. The concordance of differential expressions of these markers between the represented cancer type and others are confirmed. Successful classification of cancer types and a normal group regardless of normal tissues' origin suggested that the identified markers are cancer-specific rather than tissue-specific. CONCLUSION: Novel GCNN models have been established to predict cancer types or normal tissue based on gene expression profiles. We demonstrated the results from the TCGA dataset that these models can produce accurate classification (above 94%), using cancer-specific markers genes. The models and the source codes are publicly available and can be readily adapted to the diagnosis of cancer and other diseases by the data-driven modeling research community.

Deriving a Boolean dynamics to reveal macrophage activation with in vitro temporal cytokine expression profiles.

BACKGROUND: Macrophages show versatile functions in innate immunity, infectious diseases, and progression of cancers and cardiovascular diseases. These versatile functions of macrophages are conducted by different macrophage phenotypes classified as classically activated macrophages and alternatively activated macrophages due to different stimuli in the complex in vivo cytokine environment. Dissecting the regulation of macrophage activations will have a significant impact on disease progression and therapeutic strategy. Mathematical modeling of macrophage activation can improve the understanding of this biological process through quantitative analysis and provide guidance to facilitate future experimental design. However, few results have been reported for a complete model of macrophage activation patterns. RESULTS: We globally searched and reviewed literature for macrophage activation from PubMed databases and screened the published experimental results. Temporal in vitro macrophage cytokine expression profiles from published results were selected to establish Boolean network models for macrophage activation patterns in response to three different stimuli. A combination of modeling methods including clustering, binarization, linear programming (LP), Boolean function determination, and semi-tensor product was applied to establish Boolean networks to quantify three macrophage activation patterns. The structure of the networks was confirmed based on protein-protein-interaction databases, pathway databases, and published experimental results. Computational predictions of the network evolution were compared against real experimental results to validate the effectiveness of the Boolean network models. CONCLUSION: Three macrophage activation core evolution maps were established based on the Boolean networks using Matlab. Cytokine signatures of macrophage activation patterns were identified, providing a possible determination of macrophage activations using extracellular cytokine measurements.

California Almond Yield Prediction at the Orchard Level With a Machine Learning Approach.

California's almond growers face challenges with nitrogen management as new legislatively mandated nitrogen management strategies for almond have been implemented. These regulations require that growers apply nitrogen to meet, but not exceed, the annual N demand for crop and tree growth and nut production. To accurately predict seasonal nitrogen demand, therefore, growers need to estimate block-level almond yield early in the growing season so that timely N management decisions can be made. However, methods to predict almond yield are not currently available. To fill this gap, we have developed statistical models using the Stochastic Gradient Boosting, a machine learning approach, for early season yield projection and mid-season yield update over individual orchard blocks. We collected yield records of 185 orchards, dating back to 2005, from the major almond growers in the Central Valley of California. A large set of variables were extracted as predictors, including weather and orchard characteristics from remote sensing imagery. Our results showed that the predicted orchard-level yield agreed well with the independent yield records. For both the early season (March) and mid-season (June) predictions, a coefficient of determination (R 2) of 0.71, and a ratio of performance to interquartile distance (RPIQ) of 2.6 were found on average. We also identified several key determinants of yield based on the modeling results. Almond yield increased dramatically with the orchard age until about 7 years old in general, and the higher long-term mean maximum temperature during April-June enhanced the yield in the southern orchards, while a larger amount of precipitation in March reduced the yield, especially in northern orchards. Remote sensing metrics such as annual maximum vegetation indices were also dominant variables for predicting the yield potential. While these results are promising, further refinement is needed; the availability of larger data sets and incorporation of additional variables and methodologies will be required for the model to be used as a fertilization decision support tool for growers. Our study has demonstrated the potential of automatic almond yield prediction to assist growers to manage N adaptively, comply with mandated requirements, and ensure industry sustainability.

An Assessment of Climate Change Impacts on Los Angeles (California USA) Hospitals, Wildfires Highest Priority.

Introduction Although many studies have delineated the variety and magnitude of impacts that climate change is likely to have on health, very little is known about how well hospitals are poised to respond to these impacts. Hypothesis/Problem The hypothesis is that most modern hospitals in urban areas in the United States need to augment their current disaster planning to include climate-related impacts. METHODS: Using Los Angeles County (California USA) as a case study, historical data for emergency department (ED) visits and projections for extreme-heat events were used to determine how much climate change is likely to increase ED visits by mid-century for each hospital. In addition, historical data about the location of wildfires in Los Angeles County and projections for increased frequency of both wildfires and flooding related to sea-level rise were used to identify which area hospitals will have an increased risk of climate-related wildfires or flooding at mid-century. RESULTS: Only a small fraction of the total number of predicted ED visits at mid-century would likely to be due to climate change. By contrast, a significant portion of hospitals in Los Angeles County are in close proximity to very high fire hazard severity zones (VHFHSZs) and would be at greater risk to wildfire impacts as a result of climate change by mid-century. One hospital in Los Angeles County was anticipated to be at greater risk due to flooding by mid-century as a result of climate-related sea-level rise. CONCLUSION: This analysis suggests that several Los Angeles County hospitals should focus their climate-change-related planning on building resiliency to wildfires. Adelaine SA , Sato M , Jin Y , Godwin H . An assessment of climate change impacts on Los Angeles (California USA) hospitals, wildfires highest priority. Prehosp Disaster Med. 2017;32(5):556-562.

State feedback control design for Boolean networks.

BACKGROUND: Driving Boolean networks to desired states is of paramount significance toward our ultimate goal of controlling the progression of biological pathways and regulatory networks. Despite recent computational development of controllability of general complex networks and structural controllability of Boolean networks, there is still a lack of bridging the mathematical condition on controllability to real boolean operations in a network. Further, no realtime control strategy has been proposed to drive a Boolean network. RESULTS: In this study, we applied semi-tensor product to represent boolean functions in a network and explored controllability of a boolean network based on the transition matrix and time transition diagram. We determined the necessary and sufficient condition for a controllable Boolean network and mapped this requirement in transition matrix to real boolean functions and structure property of a network. An efficient tool is offered to assess controllability of an arbitrary Boolean network and to determine all reachable and non-reachable states. We found six simplest forms of controllable 2-node Boolean networks and explored the consistency of transition matrices while extending these six forms to controllable networks with more nodes. Importantly, we proposed the first state feedback control strategy to drive the network based on the status of all nodes in the network. Finally, we applied our reachability condition to the major switch of P53 pathway to predict the progression of the pathway and validate the prediction with published experimental results. CONCLUSIONS: This control strategy allowed us to apply realtime control to drive Boolean networks, which could not be achieved by the current control strategy for Boolean networks. Our results enabled a more comprehensive understanding of the evolution of Boolean networks and might be extended to output feedback control design.