Particulate matter forecast and prediction in Curitiba using machine learning.

Introduction: Air quality is directly affected by pollutant emission from vehicles, especially in large cities and metropolitan areas or when there is no compliance check for vehicle emission standards. Particulate Matter (PM) is one of the pollutants emitted from fuel burning in internal combustion engines and remains suspended in the atmosphere, causing respiratory and cardiovascular health problems to the population. In this study, we analyzed the interaction between vehicular emissions, meteorological variables, and particulate matter concentrations in the lower atmosphere, presenting methods for predicting and forecasting PM2.5. Methods: Meteorological and vehicle flow data from the city of Curitiba, Brazil, and particulate matter concentration data from optical sensors installed in the city between 2020 and 2022 were organized in hourly and daily averages. Prediction and forecasting were based on two machine learning models: Random Forest (RF) and Long Short-Term Memory (LSTM) neural network. The baseline model for prediction was chosen as the Multiple Linear Regression (MLR) model, and for forecast, we used the naive estimation as baseline. Results: RF showed that on hourly and daily prediction scales, the planetary boundary layer height was the most important variable, followed by wind gust and wind velocity in hourly or daily cases, respectively. The highest PM prediction accuracy (99.37%) was found using the RF model on a daily scale. For forecasting, the highest accuracy was 99.71% using the LSTM model for 1-h forecast horizon with 5 h of previous data used as input variables. Discussion: The RF and LSTM models were able to improve prediction and forecasting compared with MLR and Naive, respectively. The LSTM was trained with data corresponding to the period of the COVID-19 pandemic (2020 and 2021) and was able to forecast the concentration of PM2.5 in 2022, in which the data show that there was greater circulation of vehicles and higher peaks in the concentration of PM2.5. Our results can help the physical understanding of factors influencing pollutant dispersion from vehicle emissions at the lower atmosphere in urban environment. This study supports the formulation of new government policies to mitigate the impact of vehicle emissions in large cities.

Tradescantia response to air and soil pollution, stamen hair cells dataset and ANN color classification.

Tradescantia plant is a complex system that is sensible to environmental factors such as water supply, pH, temperature, light, radiation, impurities, and nutrient availability. It can be used as a biomonitor for environmental changes; however, the bioassays are time-consuming and have a strong human interference factor that might change the result depending on who is performing the analysis. We have developed computer vision models to study color variations from Tradescantia clone 4430 plant stamen hair cells, which can be stressed due to air pollution and soil contamination. The study introduces a novel dataset, Trad-204, comprising single-cell images from Tradescantia clone 4430, captured during the Tradescantia stamen-hair mutation bioassay (Trad-SHM). The dataset contain images from two experiments, one focusing on air pollution by particulate matter and another based on soil contaminated by diesel oil. Both experiments were carried out in Curitiba, Brazil, between 2020 and 2023. The images represent single cells with different shapes, sizes, and colors, reflecting the plant's responses to environmental stressors. An automatic classification task was developed to distinguishing between blue and pink cells, and the study explores both a baseline model and three artificial neural network (ANN) architectures, namely, TinyVGG, VGG-16, and ResNet34. Tradescantia revealed sensibility to both air particulate matter concentration and diesel oil in soil. The results indicate that Residual Network architecture outperforms the other models in terms of accuracy on both training and testing sets. The dataset and findings contribute to the understanding of plant cell responses to environmental stress and provide valuable resources for further research in automated image analysis of plant cells. Discussion highlights the impact of turgor pressure on cell shape and the potential implications for plant physiology. The comparison between ANN architectures aligns with previous research, emphasizing the superior performance of ResNet models in image classification tasks. Artificial intelligence identification of pink cells improves the counting accuracy, thus avoiding human errors due to different color perceptions, fatigue, or inattention, in addition to facilitating and speeding up the analysis process. Overall, the study offers insights into plant cell dynamics and provides a foundation for future investigations like cells morphology change. This research corroborates that biomonitoring should be considered as an important tool for political actions, being a relevant issue in risk assessment and the development of new public policies relating to the environment.

Widespread Pesticide Distribution in the European Atmosphere Questions their Degradability in Air.

Risk assessment of pesticide impacts on remote ecosystems makes use of model-estimated degradation in air. Recent studies suggest these degradation rates to be overestimated, questioning current pesticide regulation. Here, we investigated the concentrations of 76 pesticides in Europe at 29 rural, coastal, mountain, and polar sites during the agricultural application season. Overall, 58 pesticides were observed in the European atmosphere. Low spatial variation of 7 pesticides suggests continental-scale atmospheric dispersal. Based on concentrations in free tropospheric air and at Arctic sites, 22 pesticides were identified to be prone to long-range atmospheric transport, which included 15 substances approved for agricultural use in Europe and 7 banned ones. Comparison between concentrations at remote sites and those found at pesticide source areas suggests long atmospheric lifetimes of atrazine, cyprodinil, spiroxamine, tebuconazole, terbuthylazine, and thiacloprid. In general, our findings suggest that atmospheric transport and persistence of pesticides have been underestimated and that their risk assessment needs to be improved.

Fighting Fusarium Pathogens in the Era of Climate Change: A Conceptual Approach.

Fusarium head blight (FHB) caused by Fusarium pathogens is one of the most devastating fungal diseases of small grain cereals worldwide, substantially reducing yield quality and food safety. Its severity is increasing due to the climate change caused by weather fluctuations. Intensive research on FHB control methods has been initiated more than a decade ago. Since then, the environment has been rapidly changing at regional to global scales due to increasing anthropogenic emissions enhanced fertilizer application and substantial changes in land use. It is known that environmental factors affect both the pathogen virulence as well as plant resistance mechanisms. Changes in CO2 concentration, temperature, and water availability can have positive, neutral, or negative effects on pathogen spread depending on the environmental optima of the pathosystem. Hence, there is a need for studies of plant-pathogen interactions in current and future environmental context. Long-term monitoring data are needed in order to understand the complex nature of plants and its microbiome interactions. We suggest an holobiotic approach, integrating plant phyllosphere microbiome research on the ecological background. This will enable the development of efficient strategies based on ecological know-how to fight Fusarium pathogens and maintain sustainable agricultural systems.

Solar-induced chlorophyll fluorescence exhibits a universal relationship with gross primary productivity across a wide variety of biomes.

In our recent study in Global Change Biology (Li et al., ), we examined the relationship between solar-induced chlorophyll fluorescence (SIF) measured from the Orbiting Carbon Observatory-2 (OCO-2) and gross primary productivity (GPP) derived from eddy covariance flux towers across the globe, and we discovered that there is a nearly universal relationship between SIF and GPP across a wide variety of biomes. This finding reveals the tremendous potential of SIF for accurately mapping terrestrial photosynthesis globally.

Solar-induced chlorophyll fluorescence is strongly correlated with terrestrial photosynthesis for a wide variety of biomes: First global analysis based on OCO-2 and flux tower observations.

Solar-induced chlorophyll fluorescence (SIF) has been increasingly used as a proxy for terrestrial gross primary productivity (GPP). Previous work mainly evaluated the relationship between satellite-observed SIF and gridded GPP products both based on coarse spatial resolutions. Finer resolution SIF (1.3 km × 2.25 km) measured from the Orbiting Carbon Observatory-2 (OCO-2) provides the first opportunity to examine the SIF-GPP relationship at the ecosystem scale using flux tower GPP data. However, it remains unclear how strong the relationship is for each biome and whether a robust, universal relationship exists across a variety of biomes. Here we conducted the first global analysis of the relationship between OCO-2 SIF and tower GPP for a total of 64 flux sites across the globe encompassing eight major biomes. OCO-2 SIF showed strong correlations with tower GPP at both midday and daily timescales, with the strongest relationship observed for daily SIF at the 757 nm (R2  = 0.72, p < 0.0001). Strong linear relationships between SIF and GPP were consistently found for all biomes (R2  = 0.57-0.79, p < 0.0001) except evergreen broadleaf forests (R2  = 0.16, p < 0.05) at the daily timescale. A higher slope was found for C4 grasslands and croplands than for C3 ecosystems. The generally consistent slope of the relationship among biomes suggests a nearly universal rather than biome-specific SIF-GPP relationship, and this finding is an important distinction and simplification compared to previous results. SIF was mainly driven by absorbed photosynthetically active radiation and was also influenced by environmental stresses (temperature and water stresses) that determine photosynthetic light use efficiency. OCO-2 SIF generally had a better performance for predicting GPP than satellite-derived vegetation indices and a light use efficiency model. The universal SIF-GPP relationship can potentially lead to more accurate GPP estimates regionally or globally. Our findings revealed the remarkable ability of finer resolution SIF observations from OCO-2 and other new or future missions (e.g., TROPOMI, FLEX) for estimating terrestrial photosynthesis across a wide variety of biomes and identified their potential and limitations for ecosystem functioning and carbon cycle studies.

Herbivory by an Outbreaking Moth Increases Emissions of Biogenic Volatiles and Leads to Enhanced Secondary Organic Aerosol Formation Capacity.

In addition to climate warming, greater herbivore pressure is anticipated to enhance the emissions of climate-relevant biogenic volatile organic compounds (VOCs) from boreal and subarctic forests and promote the formation of secondary aerosols (SOA) in the atmosphere. We evaluated the effects of Epirrita autumnata, an outbreaking geometrid moth, feeding and larval density on herbivore-induced VOC emissions from mountain birch in laboratory experiments and assessed the impact of these emissions on SOA formation via ozonolysis in chamber experiments. The results show that herbivore-induced VOC emissions were strongly dependent on larval density. Compared to controls without larval feeding, clear new particle formation by nucleation in the reaction chamber was observed, and the SOA mass loadings in the insect-infested samples were significantly higher (up to 150-fold). To our knowledge, this study provides the first controlled documentation of SOA formation from direct VOC emission of deciduous trees damaged by known defoliating herbivores and suggests that chewing damage on mountain birch foliage could significantly increase reactive VOC emissions that can importantly contribute to SOA formation in subarctic forests. Additional feeding experiments on related silver birch confirmed the SOA results. Thus, herbivory-driven volatiles are likely to play a major role in future biosphere-vegetation feedbacks such as sun-screening under daily 24 h sunshine in the subarctic.

Elevated atmospheric CO2 concentration leads to increased whole-plant isoprene emission in hybrid aspen (Populus tremula × Populus tremuloides).

Effects of elevated atmospheric [CO2] on plant isoprene emissions are controversial. Relying on leaf-scale measurements, most models simulating isoprene emissions in future higher [CO2] atmospheres suggest reduced emission fluxes. However, combined effects of elevated [CO2] on leaf area growth, net assimilation and isoprene emission rates have rarely been studied on the canopy scale, but stimulation of leaf area growth may largely compensate for possible [CO2] inhibition reported at the leaf scale. This study tests the hypothesis that stimulated leaf area growth leads to increased canopy isoprene emission rates. We studied the dynamics of canopy growth, and net assimilation and isoprene emission rates in hybrid aspen (Populus tremula × Populus tremuloides) grown under 380 and 780 µmol mol(-1) [CO2]. A theoretical framework based on the Chapman-Richards function to model canopy growth and numerically compare the growth dynamics among ambient and elevated atmospheric [CO2]-grown plants was developed. Plants grown under elevated [CO2] had higher C : N ratio, and greater total leaf area, and canopy net assimilation and isoprene emission rates. During ontogeny, these key canopy characteristics developed faster and stabilized earlier under elevated [CO2]. However, on a leaf area basis, foliage physiological traits remained in a transient state over the whole experiment. These results demonstrate that canopy-scale dynamics importantly complements the leaf-scale processes, and that isoprene emissions may actually increase under higher [CO2] as a result of enhanced leaf area production.

Instantaneous and historical temperature effects on alpha-pinene emissions in Pinus halepensis and Quercus ilex.

We compared the role of instantaneous temperature and temperature history in the determination of alpha-pinene emissions in Mediterranean conifer Pinus halepensis that stores monoterpenes in resin ducts, and in Mediterranean broad-leaved evergreen Quercus ilex that lacks such specialized storage structures. In both species, alpha-pinene emission rates (E) exhibited a significant exponential correlation with leaf temperature and the rates of photosynthetic electron transport (Jco2+o2) started to decrease after an optimum at approximately 35 degrees C. However, there was a higher dependence of E on mean temperature of previous days than on mean temperature of current day for P. halepensis but not for Q. ilex. Jco2+o2 showed a maximum relationship to mean temperature of previous 3 and 5 days for P. halepensis and Q. ilex respectively. We conclude that although the best correlation of emission rates were found for instantaneous foliar temperatures, the effect of accumulated previous temperature conditions should also be considered in models of monoterpene emission, especially for terpene (see text) species.

Ecosystem-scale biosphere-atmosphere interactions of a hemiboreal mixed forest stand at Järvselja, Estonia.

During two measurement campaigns, from August to September 2008 and 2009, we quantified the major ecosystem fluxes in a hemiboreal forest ecosystem in Järvselja, Estonia. The main aim of this study was to separate the ecosystem flux components and gain insight into the performance of a multi-species multi-layered tree stand. Carbon dioxide and water vapor fluxes were measured using the eddy covariance method above and below the canopy in conjunction with the microclimate. Leaf and soil contributions were quantified separately by cuvette and chamber measurements, including fluxes of carbon dioxide, water vapor, nitrogen oxides, nitrous oxide, methane, ozone, sulfur dioxide, and biogenic volatile organic compounds (isoprene and monoterpenes). The latter have been as well characterized for monoterpenes in detail. Based on measured atmospheric trace gas concentrations, the flux tower site can be characterized as remote and rural with low anthropogenic disturbances. Our results presented here encourage future experimental efforts to be directed towards year round integrated biosphere-atmosphere measurements and development of process-oriented models of forest-atmosphere exchange taking the special case of a multi-layered and multi-species tree stand into account. As climate change likely leads to spatial extension of hemiboreal forest ecosystems a deep understanding of the processes and interactions therein is needed to foster management and mitigation strategies.

Leaf rust induced volatile organic compounds signalling in willow during the infection.

Plants are known to emit volatile organic compounds (VOC) in response to various biotic or abiotic stresses. Although the VOC emission in the case of insect attacks is well described, there is only little known about the impact of pathogens on plant emission. In the present study, we used a willow-leaf rust system to describe the effects of a biotrophic fungal infection on the VOC emission pattern of willow leaves. We detected that isoprene emissions from rust-infected leaves decreased threefold compared to control. The total monoterpene emissions did not change although a stress-signalling compound (Z)-beta-ocimene showed an increase in infected plants on several days. The infection also increased the emission of sesquiterpenes and lipoxygenase products (LOX) by factors of 175-fold and 10-fold, respectively. The volatile emission signals showed two clear peaks during the experiment. At 6, 7 and 12 days post-infection (dpi), the relative volatile emission signal increased to about sixfold compared to uninfected plants. These time points are directly connected to rust infection since at 6 dpi the first rust pustules appeared on the leaves and at 12 dpi necrosis had developed around several pustules. We present correlations between LOX and sesquiterpene emission signals, which suggest at least two different steps in eliciting the volatile emission.

A simple dynamic model of photosynthesis in oak leaves: coupling leaf conductance and photosynthetic carbon fixation by a variable intracellular CO2 pool.

Modelling the diurnal course of photosynthesis in oak leaves (Quercus robur L.) requires appropriate description of the dynamics of leaf photosynthesis of which diurnal variations in leaf conductance and in CO2 assimilation are essential components. We propose and analyse a simple photosynthesis model with three variables: leaf conductance (gs), the CO2 partial pressure inside the leaf (pi), and a pool of Calvin cycle intermediates (aps). The environmental factors light (I) and vapour pressure deficit (VPD) are used to formulate a target function G(I, VPD) from which the actual leaf conductance is calculated. Using this gs value and a CO2 consumption term representing CO2 fixation, a differential equation for pi is derived. Carboxylation corresponds to the sink term of the pi pool and is assumed to be feedback-inhibited by aps. This simple model is shown to produce reasonable to excellent fits to data on the diurnal time courses of photosythesis, pi and gs sampled for oak leaves.