Research on fertilization decision method for rice tillering stage based on the coupling of UAV hyperspectral remote sensing and WOFOST.

Introduction: The use of chemical fertilizers in rice field management directly affects rice yield. Traditional rice cultivation often relies on the experience of farmers to develop fertilization plans, which cannot be adjusted according to the fertilizer requirements of rice. At present, agricultural drones are widely used for early monitoring of rice, but due to their lack of rationality, they cannot directly guide fertilization. How to accurately apply nitrogen fertilizer during the tillering stage to stabilize rice yield is an urgent problem to be solved in the current large-scale rice production process. Methods: WOFOST is a highly mechanistic crop growth model that can effectively simulate the effects of fertilization on rice growth and development. However, due to its lack of spatial heterogeneity, its ability to simulate crop growth at the field level is weak. This study is based on UAV remote sensing to obtain hyperspectral data of rice canopy and assimilation with the WOFOST crop growth model, to study the decision-making method of nitrogen fertilizer application during the rice tillering stage. Extracting hyperspectral features of rice canopy using Continuous Projection Algorithm and constructing a hyperspectral inversion model for rice biomass based on Extreme Learning Machine. By using two data assimilation methods, Ensemble Kalman Filter and Four-Dimensional Variational, the inverted biomass of the rice biomass hyperspectral inversion model and the localized WOFOST crop growth model were assimilated, and the simulation results of the WOFOST model were corrected. With the average yield as the goal, use the WOFOST model to formulate fertilization decisions and create a fertilization prescription map to achieve precise fertilization during the tillering stage of rice. Results: The research results indicate that the training set R2 and RMSE of the rice biomass hyperspectral inversion model are 0.953 and 0.076, respectively, while the testing set R2 and RMSE are 0.914 and 0.110, respectively. When obtaining the same yield, the fertilization strategy based on the ENKF assimilation method applied less fertilizer, reducing 5.9% compared to the standard fertilization scheme. Discussion: This study enhances the rationality of unmanned aerial vehicle remote sensing machines through data assimilation, providing a new theoretical basis for the decision-making of rice fertilization.

Unifying gamma passing rates in patient-specific QA for VMAT lung cancer treatment based on data assimilation.

This study aimed to identify systematic errors in measurement-, calculation-, and prediction-based patient-specific quality assurance (PSQA) methods for volumetric modulated arc therapy (VMAT) on lung cancer and to standardize the gamma passing rate (GPR) by considering systematic errors during data assimilation. This study included 150 patients with lung cancer who underwent VMAT. VMAT plans were generated using a collapsed-cone algorithm. For measurement-based PSQA, ArcCHECK was employed. For calculation-based PSQA, Acuros XB was used to recalculate the plans. In prediction-based PSQA, GPR was forecasted using a previously developed GPR prediction model. The representative GPR value was estimated using the least-squares method from the three PSQA methods for each original plan. The unified GPR was computed by adjusting the original GPR to account for systematic errors. The range of limits of agreement (LoA) were assessed for the original and unified GPRs based on the representative GPR using Bland-Altman plots. For GPR (3%/2 mm), original GPRs were 94.4 ± 3.5%, 98.6 ± 2.2% and 93.3 ± 3.4% for measurement-, calculation-, and prediction-based PSQA methods and the representative GPR was 95.5 ± 2.0%. Unified GPRs were 95.3 ± 2.8%, 95.4 ± 3.5% and 95.4 ± 3.1% for measurement-, calculation-, and prediction-based PSQA methods, respectively. The range of LoA decreased from 12.8% for the original GPR to 9.5% for the unified GPR across all three PSQA methods. The study evaluated unified GPRs that corrected for systematic errors. Proposing unified criteria for PSQA can enhance safety regardless of the methods used.

ML for fast assimilation of wall-pressure measurements from hypersonic flow over a cone.

Data assimilation (DA) integrates experimental measurements into computational models to enable high-fidelity predictions of dynamical systems. However, the cost associated with solving this inverse problem, from measurements to the state, can be prohibitive for complex systems such as transitional hypersonic flows. We introduce an accurate and efficient deep-learning approach that alleviates this computational burden, and that enables approximately three orders of magnitude computational acceleration relative to variational techniques. Our method pivots on the deployment of a deep operator network (DeepONet) as an accurate, parsimonious and efficient meta-model of the compressible Navier-Stokes equations. The approach involves two main steps, each addressing specific challenges. Firstly, we reduce the computational load by minimizing the number of costly direct numerical simulations to construct a comprehensive dataset for effective supervised learning. This is achieved by optimally sampling the space of possible solutions. Secondly, we expedite the computation of high-dimensional assimilated solutions by deploying the DeepONet. This entails efficiently navigating the DeepONet's approximation of the cost landscape using a gradient-free technique. We demonstrate the successful application of this method for data assimilation of wind-tunnel measurements of a Mach 6, transitional, boundary-layer flow over a 7-degree half-angle cone.

China's Fossil Fuel CO2 Emissions Estimated Using Surface Observations of Coemitted NO2.

Accurate estimates of fossil fuel CO2 (FFCO2) emissions are of great importance for climate prediction and mitigation regulations but remain a significant challenge for accounting methods relying on economic statistics and emission factors. In this study, we employed a regional data assimilation framework to assimilate in situ NO2 observations, allowing us to combine observation-constrained NOx emissions coemitted with FFCO2 and grid-specific CO2-to-NOx emission ratios to infer the daily FFCO2 emissions over China. The estimated national total for 2016 was 11.4 PgCO2·yr-1, with an uncertainty (1σ) of 1.5 PgCO2·yr-1 that accounted for errors associated with atmospheric transport, inversion framework parameters, and CO2-to-NOx emission ratios. Our findings indicated that widely used "bottom-up" emission inventories generally ignore numerous activity level statistics of FFCO2 related to energy industries and power plants in western China, whereas the inventories are significantly overestimated in developed regions and key urban areas owing to exaggerated emission factors and inexact spatial disaggregation. The optimized FFCO2 estimate exhibited more distinct seasonality with a significant increase in emissions in winter. These findings advance our understanding of the spatiotemporal regime of FFCO2 emissions in China.

Convergence in simulating global soil organic carbon by structurally different models after data assimilation.

Current biogeochemical models produce carbon-climate feedback projections with large uncertainties, often attributed to their structural differences when simulating soil organic carbon (SOC) dynamics worldwide. However, choices of model parameter values that quantify the strength and represent properties of different soil carbon cycle processes could also contribute to model simulation uncertainties. Here, we demonstrate the critical role of using common observational data in reducing model uncertainty in estimates of global SOC storage. Two structurally different models featuring distinctive carbon pools, decomposition kinetics, and carbon transfer pathways simulate opposite global SOC distributions with their customary parameter values yet converge to similar results after being informed by the same global SOC database using a data assimilation approach. The converged spatial SOC simulations result from similar simulations in key model components such as carbon transfer efficiency, baseline decomposition rate, and environmental effects on carbon fluxes by these two models after data assimilation. Moreover, data assimilation results suggest equally effective simulations of SOC using models following either first-order or Michaelis-Menten kinetics at the global scale. Nevertheless, a wider range of data with high-quality control and assurance are needed to further constrain SOC dynamics simulations and reduce unconstrained parameters. New sets of data, such as microbial genomics-function relationships, may also suggest novel structures to account for in future model development. Overall, our results highlight the importance of observational data in informing model development and constraining model predictions.

Imitating and exploring the human brain's resting and task-performing states via brain computing: scaling and architecture.

A computational human brain model with the voxel-wise assimilation method was established based on individual structural and functional imaging data. We found that the more similar the brain model is to the biological counterpart in both scale and architecture, the more similarity was found between the assimilated model and the biological brain both in resting states and during tasks by quantitative metrics. The hypothesis that resting state activity reflects internal body states was validated by the interoceptive circuit's capability to enhance the similarity between the simulation model and the biological brain. We identified that the removal of connections from the primary visual cortex (V1) to downstream visual pathways significantly decreased the similarity at the hippocampus between the model and its biological counterpart, despite a slight influence on the whole brain. In conclusion, the model and methodology present a solid quantitative framework for a digital twin brain for discovering the relationship between brain architecture and functions, and for digitally trying and testing diverse cognitive, medical and lesioning approaches that would otherwise be unfeasible in real subjects.

Coupling an agent-based model and an ensemble Kalman filter for real-time crowd modelling.

Agent-based modelling has emerged as a powerful tool for modelling systems that are driven by discrete, heterogeneous individuals and has proven particularly popular in the realm of pedestrian simulation. However, real-time agent-based simulations face the challenge that they will diverge from the real system over time. This paper addresses this challenge by integrating the ensemble Kalman filter (EnKF) with an agent-based crowd model to enhance its accuracy in real time. Using the example of Grand Central Station in New York, we demonstrate how our approach can update the state of an agent-based model in real time, aligning it with the evolution of the actual system. The findings reveal that the EnKF can substantially improve the accuracy of agent-based pedestrian simulations by assimilating data as they evolve. This approach not only offers efficiency advantages over existing methods but also presents a more realistic representation of a complex environment than most previous attempts. The potential applications of this method span the management of public spaces under 'normality' to exceptional circumstances such as disaster response, marking a significant advancement for real-time agent-based modelling applications.

Invert global and China's terrestrial carbon fluxes over 2019-2021 based on assimilating richer atmospheric CO2 observations.

With China's commitment to reach carbon peak by 2030 and achieve carbon neutrality by 2060, it is particularly important to obtain terrestrial ecosystem carbon fluxes with low uncertainty both globally and in China. The use of more observation data may help reduce the uncertainty of inverting carbon fluxes. This study uses the observation data from global stations, background stations and provincial stations in China, as well as the OCO-2 satellite, and uses the China Carbon Monitoring, Verification and Supporting System for Global (CCMVS-G) to estimate the carbon fluxes of global and Chinese terrestrial ecosystems from 2019 to 2021. The results revealed that the global terrestrial ecosystem carbon sink was approximately -3.40 Pg C/yr from 2019 to 2021. The carbon sinks in the Northern Hemisphere are large, especially in Asia, North America, and Europe. From 2019 to 2021, the carbon sink of China's terrestrial ecosystem was approximately -0.44 Pg C/yr. Carbon sinks exhibit significant seasonal and interannual variations in China. After assimilating the observation data, the uncertainty of the posterior flux is smaller than that of the prior flux, a more reasonable distribution of carbon sources and sinks can be obtained, and more accurate boundary conditions can be provided for the China Carbon Monitoring, Verification and Supporting System for Regional (CCMVS-R). In the future, it is important to establish a well-designed CO2 ground-based observation network.

A computational study of right ventricular mechanics in a rat model of pulmonary arterial hypertension.

Pulmonary arterial hypertension (PAH) presents a significant challenge to right ventricular (RV) function due to progressive pressure overload, necessitating adaptive remodeling in the form of increased wall thickness, enhanced myocardial contractility and stiffness to maintain cardiac performance. However, the impact of these remodeling mechanisms on RV mechanics in not clearly understood. In addition, there is a lack of quantitative understanding of how each mechanism individually influences RV mechanics. Utilizing experimental data from a rat model of PAH at three distinct time points, we developed biventricular finite element models to investigate how RV stress and strain evolved with PAH progression. The finite element models were fitted to hemodynamic and morphological data to represent different disease stages and used to analyze the impact of RV remodeling as well as the altered RV pressure. Furthermore, we performed a number of theoretical simulation studies with different combinations of morphological and physiological remodeling, to assess and quantify their individual impact on overall RV load and function. Our findings revealed a substantial 4-fold increase in RV stiffness and a transient 2-fold rise in contractility, which returned to baseline by week 12. These changes in RV material properties in addition to the 2-fold increase in wall thickness significantly mitigated the increase in wall stress and strain caused by the progressive increase in RV afterload. Despite the PAH-induced cases showing increased wall stress and strain at end-diastole and end-systole compared to the control, our simulations suggest that without the observed remodeling mechanisms, the increase in stress and strain would have been much more pronounced. Our model analysis also indicated that while changes in the RV's material properties-particularly increased RV stiffness - have a notable effect on its mechanics, the primary compensatory factor limiting the stress and strain increase in the early stages of PAH was the significant increase in wall thickness. These findings underscore the importance of RV remodeling in managing the mechanical burden on the right ventricle due to pressure overload.

Improved data assimilation for algal bloom dynamics simulation in the Three Gorges Reservoir using particle filter.

Algal blooms have been increasingly prevalent in recent years, especially in lakes and reservoirs; their accurate prediction is essential for preserving water quality. In this study, the observed chlorophyll a (chl-a) levels were assimilated into the Environmental Fluid Dynamics Code (EFDC) of algal bloom dynamics by using a particle filter (PF), and the state variables of water quality and model parameters were simultaneously updated to achieve enhanced algal bloom predictive performance. The developed data assimilation system for algal blooms was applied to Xiangxi Bay (XXB) in the Three Gorges Reservoir (TGR). The results show that the ensemble mean accuracy and reliability of the confidence intervals of the predicted state variables, including chl-a and indirectly updated phosphate (PO4), ammonium (NH4), and nitrate (NO3) levels, were considerably improved after PF assimilation. Thus, PF assimilation is an effective tool for the dynamic correction of parameters to represent their inherent variations. Increased assimilation frequency can effectively suppress the accumulation of model errors; therefore, the use of high-frequency water quality data for assimilation is recommended to ensure more accurate and reliable algal bloom prediction.

A mathematical model for predicting the spatiotemporal response of breast cancer cells treated with doxorubicin.

Tumor heterogeneity contributes significantly to chemoresistance, a leading cause of treatment failure. To better personalize therapies, it is essential to develop tools capable of identifying and predicting intra- and inter-tumor heterogeneities. Biology-inspired mathematical models are capable of attacking this problem, but tumor heterogeneity is often overlooked in in-vivo modeling studies, while phenotypic considerations capturing spatial dynamics are not typically included in in-vitro modeling studies. We present a data assimilation-prediction pipeline with a two-phenotype model that includes a spatiotemporal component to characterize and predict the evolution of in-vitro breast cancer cells and their heterogeneous response to chemotherapy. Our model assumes that the cells can be divided into two subpopulations: surviving cells unaffected by the treatment, and irreversibly damaged cells undergoing treatment-induced death. MCF7 breast cancer cells were previously cultivated in wells for up to 1000 hours, treated with various concentrations of doxorubicin and imaged with time-resolved microscopy to record spatiotemporally-resolved cell count data. Images were used to generate cell density maps. Treatment response predictions were initialized by a training set and updated by weekly measurements. Our mathematical model successfully calibrated the spatiotemporal cell growth dynamics, achieving median [range] concordance correlation coefficients of > .99 [.88, >.99] and .73 [.58, .85] across the whole well and individual pixels, respectively. Our proposed data assimilation-prediction approach achieved values of .97 [.44, >.99] and .69 [.35, .79] for the whole well and individual pixels, respectively. Thus, our model can capture and predict the spatiotemporal dynamics of MCF7 cells treated with doxorubicin in an in-vitro setting.

On a framework of data assimilation for hyperparameter estimation of spiking neuronal networks.

When handling real-world data modeled by a complex network dynamical system, the number of the parameters is often much more than the size of the data. Therefore, in many cases, it is impossible to estimate these parameters and the exact value of each parameter is frequently less interesting than the distribution of the parameters. In this paper, we aim to estimate the distribution of the parameters in the mesoscopic neuronal network model from the macroscopic experimental data, for example, the BOLD (blood oxygen level dependent) signal. Herein, we assume that the parameters of the neurons and synapses are inhomogeneous but independently and identically distributed from certain distributions with unknown hyperparameters. Thus, we estimate these hyperparameters of the distributions of the parameters, instead of estimating the parameters themselves. We formulate this problem under the framework of data assimilation and hierarchical Bayesian method and present an efficient method named Hierarchical Data Assimilation (HDA) to conduct the statistical inference on the neuronal network model with the BOLD signal data simulated by the hemodynamic model. We consider the Leaky Integral-Fire (LIF) neuronal networks with four synapses and show that the proposed algorithm can estimate the BOLD signals and the hyperparameters with high preciseness. In addition, we discuss the influence on the performance of the algorithm configuration and the LIF network model setup.

A decadal atmospheric ammonia reanalysis product in China.

Atmospheric ammonia has great environmental implications due to its important role in ecosystem and nitrogen cycle, as well as contribution to formation of secondary particles. China is recognized as a hotspot of NH3 pollution owing to agricultural and livestock intensification. In the quest to achieve a comprehensive understanding of atmospheric ammonia load and to quantify its environmental impacts in China, relying solely either on existing measurements or on model simulations falls short. Their limitations, either in spatial coverage and integrity or in data quality, fails to meet the needs. Available reanalysis products exhibit a marked deficiency in ammonia data. We therefore aim to propose an integrated ammonia reanalysis product in China, adeptly melding satellite observations from the Infrared Atmospheric Sounding Interferometer (IASI) NH3 retrievals with chemical transport model simulation, capitalizing on the robust Ensemble Kalman Filter (EnKF) data assimilation methodology. The product is validated in high quality via the comparison against independent measurements from ground monitoring stations. Spanning a decade from 2013 to 2022, our reanalysis uncovers not just the spatial intricacies of NH3 concentrations but also their temporal dynamics. Our findings pinpointed the spatial disparities in atmospheric ammonia intensities, highlighting regional hotspots in the NCP, SCB, and Northeast China, and identified annual and seasonal patterns. Our research provides crucial insights for shaping future NH3 pollution prevention and control strategies in China.

Global groundwater droughts are more severe than they appear in hydrological models: An investigation through a Bayesian merging of GRACE and GRACE-FO data with a water balance model.

Realistic representation of hydrological drought events is increasingly important in world facing decreased freshwater availability. Index-based drought monitoring systems are often adopted to represent the evolution and distribution of hydrological droughts, which mainly rely on hydrological model simulations to compute these indices. Recent studies, however, indicate that model derived water storage estimates might have difficulties in adequately representing reality. Here, a novel Markov Chain Monte Carlo - Data Assimilation (MCMC-DA) approach is implemented to merge global Terrestrial Water Storage (TWS) changes from the Gravity Recovery And Climate Experiment (GRACE) and its Follow On mission (GRACE-FO) with the water storage estimations derived from the W3RA water balance model. The modified MCMC-DA derived summation of deep-rooted soil and groundwater storage estimates is then used to compute 0.5∘ standardized groundwater drought indices globally to show the impact of GRACE/GRACE-FO DA on a global index-based hydrological drought monitoring system. Our numerical assessment covers the period of 2003-2021, and shows that integrating GRACE/GRACE-FO data modifies the seasonality and inter-annual trends of water storage estimations. Considerable increases in the length and severity of extreme droughts are found in basins that exhibited multi-year water storage fluctuations and those affected by climate teleconnections.

Developments of inverse analysis by Kalman filters and Bayesian methods applied to geotechnical engineering.

The present paper reviews recent activities on inverse analysis strategies in geotechnical engineering using Kalman filters, nonlinear Kalman filters, and Markov chain Monte Carlo (MCMC)/Hamiltonian Monte Carlo (HMC) methods. Nonlinear Kalman filters with finite element method (FEM) broaden the choices of unknowns to be determined for not only parameters but also initial and/or boundary conditions, and the use of the posterior probability of the state variables can be widely applied to, for example, the decision making for design changes. The relevance of the unknowns and the observed values and the selection of the best sensor locations are some of the considerations made while using the Kalman filter FEM. This paper demonstrates several real-world geotechnical applications of the nonlinear Kalman filter and the MCMC with FEM. Future studies should focus on the following areas: attaining excellent performance for long-term forecasts using short-term observation and developing a viable method for selecting equations that describe physical phenomena and constitutive models.

A methodology of phenotyping ICU patients from EHR data: High-fidelity, personalized, and interpretable phenotypes estimation.

OBJECTIVE: Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR). METHODS: A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation. RESULTS: The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83%±27%. CONCLUSION: The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

A new ensemble-based targeted observational method and its application in the TPOS 2020.

Ensemble Kalman filter-based targeted observation is one of the best methods for determining the optimal observational array for oceanic buoy deployment. This study proposes a new algorithm suitable for a 'cross-region and cross-variable' approach by introducing a projection operator into the optimization process. A targeted observational analysis was conducted for El Niño-Southern Oscillation (ENSO) events in the tropical western Pacific for the Tropical Pacific Observation System (TPOS) 2020. The prediction target was at the Niño 3.4 region and the first 10 optimal observational sites detected reduced initial uncertainties by 70%, with the best observational array located where the Rossby wave signal dominates. At the vertical level, the most significant contribution was derived from observations near the thermocline. This study provides insights into understanding ENSO-related variability and offers a practical approach to designing an optimal mooring array. It serves as a scientific guidance for designing a TPOS observation network.

A method for estimating yield of maize inbred lines by assimilating WOFOST model with Sentinel-2 satellite data.

Maize is the most widely planted food crop in China, and maize inbred lines, as the basis of maize genetic breeding and seed breeding, have a significant impact on China's seed security and food safety. Satellite remote sensing technology has been widely used for growth monitoring and yield estimation of various crops, but it is still doubtful whether the existing remote sensing monitoring means can distinguish the growth difference between maize inbred lines and hybrids and accurately estimate the yield of maize inbred lines. This paper explores a method for estimating the yield of maize inbred lines based on the assimilation of crop models and remote sensing data, initially solves the problem. At first, this paper analyzed the WOFOST(World Food Studies)model parameter sensitivity and used the MCMC(Markov Chain Monte Carlo) method to calibrate the sensitive parameters to obtain the parameter set of maize inbred lines differing from common hybrid maize; then the vegetation indices were selected to establish an empirical model with the measured LAI(Leaf Area Index) at three key development stages to obtain the remotely sensed estimated LAI; finally, the yield of maize inbred lines in the study area was estimated and mapped pixel by pixel using the EnKF(Ensemble Kalman Filter) data assimilation algorithm. Also, this paper compares a method of assimilation by setting a single parameter. Instead of the WOFOST parameter optimization process, a parameter representing the growth weakness of the inbred lines was set in WOFOST to distinguish the inbred lines from the hybrids. The results showed that the yield estimated by the two methods compared with the field measured yield data had R2: 0.56 and 0.18, and RMSE: 684.90 Kg/Ha and 949.95 Kg/Ha, respectively, which proved that the crop growth model of maize inbred lines established in this study combined with the data assimilation method could initially achieve the growth monitoring and yield estimation of maize inbred lines.

Low-Cost Particulate Matter Sensors for Monitoring Residential Wood Burning.

Conventional monitoring systems for air quality, such as reference stations, provide reliable pollution data in urban settings but only at relatively low spatial density. This study explores the potential of low-cost sensor systems (LCSs) deployed at homes of residents to enhance the monitoring of urban air pollution caused by residential wood burning. We established a network of 28 Airly (Airly-GSM-1, SP. Z o.o., Poland) LCSs in Kristiansand, Norway, over two winters (2021-2022). To assess performance, a gravimetric Kleinfiltergerät measured the fine particle mass concentration (PM2.5) in the garden of one participant's house for 4 weeks. Results showed a sensor-to-reference correlation equal to 0.86 for raw PM2.5 measurements at daily resolution (bias/RMSE: 9.45/11.65 µg m-3). High-resolution air quality maps at a 100 m resolution were produced by combining the output of an air quality model (uEMEP) using data assimilation techniques with the network data that were corrected and calibrated by using a proposed five-step network data processing scheme. Leave-one-out cross-validation demonstrated that data assimilation reduced the model's RMSE, MAE, and bias by 44-56, 38-48, and 41-52%, respectively.

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data.

This paper proposes an Informer-based temperature prediction model to leverage data from an automatic weather station (AWS) and a local data assimilation and prediction system (LDAPS), where the Informer as a variant of a Transformer was developed to better deal with time series data. Recently, deep-learning-based temperature prediction models have been proposed, demonstrating successful performances, such as conventional neural network (CNN)-based models, bi-directional long short-term memory (BLSTM)-based models, and a combination of both neural networks, CNN-BLSTM. However, these models have encountered issues due to the lack of time data integration during the training phase, which also lead to the persistence of a long-term dependency problem in the LSTM models. These limitations have culminated in a performance deterioration when the prediction time length was extended. To overcome these issues, the proposed model first incorporates time-periodic information into the learning process by generating time-periodic information and inputting it into the model. Second, the proposed model replaces the LSTM with an Informer as an alternative to mitigating the long-term dependency problem. Third, a series of fusion operations between AWS and LDAPS data are executed to examine the effect of each dataset on the temperature prediction performance. The performance of the proposed temperature prediction model is evaluated via objective measures, including the root-mean-square error (RMSE) and mean absolute error (MAE) over different timeframes, ranging from 6 to 336 h. The experiments showed that the proposed model relatively reduced the average RMSE and MAE by 0.25 °C and 0.203 °C, respectively, compared with the results of the CNN-BLSTM-based model.