Data Gaps Research Articles

Do traffic flow states follow Markov properties? A high-order spatiotemporal traffic state reconstruction approach for traffic prediction and imputation

Assessing traffic states accurately is challenging due to the complex, high-dimensional, and nonlinear nature of traffic systems. This study introduces the innovative High-Order Spatiotemporal Traffic State Reconstruction (HOSTSR) algorithm, designed to track and predict traffic flow dynamics effectively. It combines phase space reconstruction with time delays and high-order neighborhood concepts from graph theory to improve traffic state assessments' accuracy. The algorithm's effectiveness is validated using chi-square tests and the Chapman-Kolmogorov equation to confirm the Markovian properties of traffic flows. A lean autoencoder, informed by prior Markov knowledge of traffic states, is developed for mapping traffic states to real traffic data, proving highly effective for traffic data imputation due to the Markov model's memoryless property. Experimental results from the PeMSD04 and PeMSD08 datasets show that HOSTSR outperforms traditional state reconstruction methods based on delayed coordinate embedding in predicting future traffic flow state based on four key metrics. The autoencoder framework, guided by prior Markov knowledge, shows significant advantages in addressing traffic data gaps in different cases over six baseline models. Gradient sensitivity analysis further evaluates the impact of prior knowledge on improving the autoencoder's interpretability for interpolation efforts.

Research on Sugarcane Recognition based on Joint Spatial and Spectral Information from Satellite-Based Hyperspectral Imagery

Abstract. The total amount of sugarcane planting in China ranks third in the world, and Guangxi is the largest sugarcane planting base in China. In order to help the Guangxi government and industry better understand the annual planting distribution and scale of sugarcane in the whole region, it is convenient to optimize the planting structure and improve the efficiency of resource utilization, so as to ensure the stable development of Guangxi sugar industry. Based on the satellite-based hyperspectral image data of ' Zhuhai No.1 ', this paper carries out sugarcane recognition and area extraction, which fills the application gap of satellite-based hyperspectral image data in extracting sugarcane area in China. A globally optimized extended random walk model was used to identify and extract sugarcane by combining the spatial-spectral information of hyperspectral imagery. Firstly, the Initial probability estimation is performed using the LOR classifier, and then use the data after MNF dimensionality reduction to construct a weighted graph, and finally the probability optimization and recognition are carried out based on the extended random walk model. The results show that the spatial-spectral joint method based on extended random walk can effectively identify sugarcane, and the sugarcane recognition accuracy of 2021 year image can reach 91.4%, the misrecognition rate is 2.8%; the sugarcane recognition accuracy of 2020 year image can reach 90.5 %, the misrecognition rate is 3.1%.

Towards Transnational Fairness in Machine Learning: A Case Study in Disaster Response Systems

Research on fairness in machine learning (ML) has been largely focusing on individual and group fairness. With the adoption of ML-based technologies as assistive technology in complex societal transformations or crisis situations on a global scale these existing definitions fail to account for algorithmic fairness transnationally. We propose to complement existing perspectives on algorithmic fairness with a notion of transnational algorithmic fairness and take first steps towards an analytical framework. We exemplify the relevance of a transnational fairness assessment in a case study on a disaster response system using images from online social media. In the presented case, ML systems are used as a support tool in categorizing and classifying images from social media after a disaster event as an almost instantly available source of information for coordinating disaster response. We present an empirical analysis assessing the transnational fairness of the application’s outputs-based on national socio-demographic development indicators as potentially discriminatory attributes. In doing so, the paper combines interdisciplinary perspectives from data analytics, ML, digital media studies and media sociology in order to address fairness beyond the technical system. The case study investigated reflects an embedded perspective of peoples’ everyday media use and social media platforms as the producers of sociality and processing data-with relevance far beyond the case of algorithmic fairness in disaster scenarios. Especially in light of the concentration of artificial intelligence (AI) development in the Global North and a perceived hegemonic constellation, we argue that transnational fairness offers a perspective on global injustices in relation to AI development and application that has the potential to substantiate discussions by identifying gaps in data and technology. These analyses ultimately will enable researchers and policy makers to derive actionable insights that could alleviate existing problems with fair use of AI technology and mitigate risks associated with future developments.

Pulses in Uttarakhand: Has Their Potential Been Tapped Enough to Attain Food and Nutritional Security?

Background: Malnutrition is a global health crisis and Uttarakhand state is no exception. Besides the implementation of various government schemes for eradication of undernutrition is at very slow pace calls for analyzing the present situation and future prospects of food crops. In this regard, Uttarakhand a hilly state with many agricultural constraints needs special attention. Pulses known for rich protein and micronutrient content can serve as an excellent source for mitigating protein deficiency and attaining food and nutrition security. Various pulses in different cropping pattern are being grown in the state. The current study aims at exploring the dynamics, diversification and decomposition of pulses in Uttarakhand and their role in providing food and nutritional security. Methods: Secondary data related to area under pulses, production and yield were taken from official website of Agriculture department, Government of Uttarakhand. The data gaps were filled through linear interpolation. Production of total pulses was linearly extrapolated to estimate pulses production for 2035-36. Growth and instability, diversification and decomposition of pulses were analyzed. The Food and Nutritional security statistics were taken from directorate of Economics and Statistics, Government of Uttarakhand and explored in relation to pulses. Result: It was found that the state is faring well in production of pulses as an increase in absolute area, production, yield and proportion of pulses in gross sown area was observed. High pulse diversification was seen. However, a decline in all major pulse-based cropping systems was seen. Moreover, in the state, where 31% of the population lacks adequate protein intake, there is a pressing need to enhance the availability, accessibility and absorption of protein-rich pulses, particularly for vegetarians. Additionally, it is essential to reevaluate the state’s food and nutrition security status in alignment with the updated guidelines from ICMR-NIN in 2020.

Exploring age and gender variations in root canal morphology of maxillary premolars in Saudi sub population: a cross-sectional CBCT study

BackgroundIn complex teeth like maxillary premolars, endodontic treatment success depends on a complete comprehension of root canal anatomy. The research on mandibular premolars’ root canal anatomy has been extensive and well-documented in existing literature. However, there appears to be a notable gap in available data concerning the root canal anatomy of maxillary premolars. This study aimed to explore the root canal morphology of maxillary premolars using cone-beam computed tomography (CBCT) imaging, considering age and gender variations.MethodsFrom 500 patient CBCT scans, 787 maxillary premolar teeth were evaluated. The sample was divided by gender and age (10–20, 21–30, 31–40, 41–50, 51–60, and 61 years and older). Ahmed et al. classification system was used to record root canal morphology.ResultsThe most frequent classifications for right maxillary 1st premolars were 2MPM1 B1 L1 (39.03%) and 1MPM1 (2.81%), while the most frequent classifications for right maxillary 2nd premolars were 2MPM1 B1 L1 (39.08%) and 1MPM1 (17.85%). Most of the premolars typically had two roots (left maxillary first premolars: 81.5%, left maxillary second premolars: 82.7%, right maxillary first premolars: 74.4%, right maxillary second premolars: 75.7%). Left and right maxillary 1st premolars for classes 1MPM1 and 1MPM1–2−1 showed significant gender differences. For classifications 1MPM1 and 1MPM1–2−1, age-related changes were seen in the left and right maxillary first premolars.ConclusionThis study provides novel insights into the root canal anatomy of maxillary premolars within the Saudi population, addressing a notable gap in the literature specific to this demographic. Through CBCT imaging and analysis of large sample sizes, the complex and diverse nature of root canal morphology in these teeth among Saudi individuals is elucidated. The findings underscore the importance of CBCT imaging in precise treatment planning and decision-making tailored to the Saudi population. Consideration of age and gender-related variations further enhances understanding and aids in personalized endodontic interventions within this demographic.

A Flexible, Multi-Instrument Optimal Estimation Retrieval for Wind Profiles

Abstract Instruments such as Doppler lidars, radar wind profilers and uncrewed aircraft systems could be used in observation networks to fill in the temporal and spatial gap that exists for low level wind observations. These instruments, however, do not directly observe the wind and require a retrieval to be used to obtain wind estimates from their observations. Also, the depth and uncertainty of observations collected by these instruments varies depending on the environment that they are sampling. Optimal estimation is a variational retrieval method that combines information from a prior data set and observations to retrieve an atmospheric state. This technique can be beneficial to use when observations have large uncertainties or provide insufficient information to obtain the atmospheric state by themselves. A new optimal estimation retrieval for obtaining wind profiles from typical lower atmosphere wind profiling instrumentation has been developed. This retrieval allows for more observations from wind profiling instrumentation to be used when retrieving wind profiles, increases the depth of retrieved profiles, and eliminates vertical data gaps. This retrieval can also be used to easily combine observations from different instruments or even with model data to create combined data wind retrievals that leverage the strengths of the different data sources to retrieve a wind profile that is superior to those obtained by the individual observations or data sources. It is envisioned that this retrieval will be continued to be developed and maintained as community software as lower atmosphere wind observing capabilities further develop and expand.

Shielding Healthcare Data Strategies for Preventing Breaches

As the healthcare sector embraces digital transformation, the risk of cyberattacks on sensitive patient data escalates. This paper presents a comprehensive analysis of contemporary strategies and technologies employed to mitigate data breaches in healthcare. Through an extensive review of 70 research papers, we identify a strong focus on securing electronic health records, data storage systems, access controls, and personal health information. Noteworthy trends include the integration of advanced technologies such as Blockchain and Artificial Intelligence, coupled with robust encryption methods, to fortify data security. Our analysis underscores the urgent need for innovative approaches to combat prevalent cybersecurity threats, particularly targeting hacking incidents and unauthorized access. Furthermore, we emphasize the ongoing evolution of mitigation strategies and the imperative of continual technological advancements to safeguard healthcare data effectively. This paper also outlines future research directions, highlighting areas for further technological innovation and addressing existing gaps in data breach prevention measures.

Predicting air quality trends in Malaysia’s largest cities: the role of urban population dynamics and COVID-19 effects

This paper aims to explore the relationship between the Air Quality Index (AQI), COVID-19 incidence rates, and population density within Malaysia’s ten most populous cities from January 2018 to December 2021. Data were sourced from the Department of Statistics Malaysia, the World Air Quality Index Project, and Our World in Statistics. The methodology integrated population-based city classification and AQI assessment, cluster analysis through SPSS, and Generalized Additive Mixed Model (GAMM) analysis using R Studio despite encountering a data gap in AQI for five months in 2019. Cities were organized into three clusters based on their AQI: Cluster One included Ipoh, Penang, Kuala Lumpur, and Melaka, Cluster Two comprised Kuantan, Seremban, Johor Bahru, and Kota Bharu, Cluster Three featured Kota Kinabalu and Kuching. GAMM analysis revealed prediction accuracies for AQI variations of 58%, 60%, and 41% for the respective clusters, indicating a notable impact of population density on air quality. AQI variations remained unaffected by COVID-19, with a forecasted improvement in air quality across all clusters. The paper presents novel insights into the negligible impact of COVID-19 on AQI variations and underscores the predictive power of population dynamics on urban air quality, offering valuable perspectives for environmental and urban planning.

A global time series of traffic volumes on extra-urban roads

Traffic on roads outside of urban areas (i.e. extra-urban roads) can have major ecological and environmental impacts on agricultural, forested, and natural areas. Yet, data on extra-urban traffic volumes is lacking in many regions. To address this data gap, we produced a global time-series of traffic volumes (Annual Average Daily Traffic; AADT) on all extra-urban highways, primary roads, and secondary roads for the years 1975, 1990, 2000 and 2015. We constructed time series of road networks from existing global datasets on roads, population density, and socio-economic indicators, and combined these with a large collection of empirical AADT data from all continents except Antarctica. We used quantile regression forests to predict the median and 5% and 95% prediction intervals of AADT on each road section. The validation accuracy of the model was high (pseudo-R2 = 0.7407) and AADT predictions from 1975 were also accurate. The resulting map series provides standardised and fine-scaled information on the development of extra-urban road traffic and has a wide variety of practical and scientific applications.

Per- and polyfluoroalkyl substances alter innate immune function: evidence and data gaps

Per- and polyfluoroalkyl substances (PFASs) are a large class of compounds used in a variety of processes and consumer products. Their unique chemical properties make them ubiquitous and persistent environmental contaminants while also making them economically viable and socially convenient. To date, several reviews have been published to synthesize information regarding the immunotoxic effects of PFASs on the adaptive immune system. However, these reviews often do not include data on the impact of these compounds on innate immunity. Here, current literature is reviewed to identify and incorporate data regarding the effects of PFASs on innate immunity in humans, experimental models, and wildlife. Known mechanisms by which PFASs modulate innate immune function are also reviewed, including disruption of cell signaling, metabolism, and tissue-level effects. For PFASs where innate immune data are available, results are equivocal, raising additional questions about common mechanisms or pathways of toxicity, but highlighting that the innate immune system within several species can be perturbed by exposure to PFASs. Recommendations are provided for future research to inform hazard identification, risk assessment, and risk management practices for PFASs to protect the immune systems of exposed organisms as well as environmental health.

A changing river: Long‐term changes of sinuosity and land cover in the Navasota River Watershed, Texas

AbstractThe Navasota River Basin, itself a tributary of the Brazos River in Texas, is a dynamic watershed undergoing many natural and anthropogenic changes. Local stakeholder involvement in this watershed is quite high, and many landowners in the southern portion of the watershed have concerns regarding the increasing frequency and duration of flooding on private property adjacent to the river, often attributing these impacts to the construction of the Lake Limestone dam. In this study, we examine historical flow data, channel morphology, land use/land cover, and precipitation. Our findings indicate that while there appears to be increasing flow in the northern portion of the watershed, temporal data gaps near the watershed outfall prevent the indication of such a trend in the southern portion of the watershed. Nevertheless, other natural and anthropogenic factors are evident in the watershed that may have a significant influence on downstream flooding. Overall river sinuosity (meandering) declined over the study period, with some river segments encountering significant straightening. Total river length declined by 4.3 km from 1972 to 2020. The number and length of offtake channels also decreased substantially during this period. Land use/land cover use shifted dramatically, with a 39.2% increase in impervious cover and a 12.5% decrease in herbaceous cover since 1972. Finally, yearly precipitation increased, with the change point occurring in 1972. Our findings suggest that the shortening and straightening of the river has reduced its volumetric capacity over time. Coupled with increasing impervious surface cover and precipitation, more water is being delivered downstream at a rate exceeding the watershed's ability to discharge it, thereby contributing to flooding issues expressed by stakeholders. We recommend that bathymetric data and supplemental flow monitoring and modeling within the watershed is needed to fully understand how anthropogenic and natural forces may further affect streamflow in the future.

Conveying Risks of Harm in Alzheimer Disease by Amyloid Lowering

This Viewpoint discusses how data gaps in published research impede clinicians’ ability to clearly discuss the risks and benefits of amyloid-lowering drugs for treating Alzheimer disease.

The AfCFTA tariff offers: Current state and first revelations about members' stances towards openness and protectionism

AbstractMost signatories of the African Continental Free Trade Area (AfCFTA) agreement have submitted tariff concession offers, as published on the AfCFTA Secretariat's website. Over a year since the AfCFTA came into effect, it is time to take stock of these submissions and assess the data with respect to members' stances towards fostering intra‐African trade through openness on the one hand and maintaining protection against competing imports and revenues from import tariffs on the other. Combining the offers with corresponding trade and tariff data, we find that there are both significant data gaps and inconsistencies with the AfCFTA's trade liberalisation modalities and the trade classification standard. Constructing two tariff schedules, one which repairs the offers for compliance with the modalities and another that maximises the import tariff revenue retained as a benchmark, the analysis confirms that the modalities require regions to liberalise strongly, but most opt to liberalise even more and earlier than necessary. Stances towards freer trade, however, differ markedly between regions. Deriving a measure of liberalisation stance from the schedules above and associating it with trade, economic and geographic indicators reveals patterns that suggest potential motivations for the stances of some country groups.

Synthesis of Radiolabeled [14C]Rimsulfuron and Stable Isotope Labeled Rimsulfuron-[M + 3] to Support Crop Metabolism Studies for Reregistration.

Rimsulfuron is a sulfonylurea herbicide that controls grass and broadleaf weeds in maize, potatoes, fruits, nuts, and other crops. It can also be used as a burndown herbicide to clear invasive weed species along roadsides and other nonagricultural land. Rimsulfuron acts as an acetolactase synthase (ALS) inhibitor, blocking the synthesis of essential amino acids required for plant growth. As is common practice, rimsulfuron has been subject to periodic reviews by regulatory agencies for reregistration since its introduction into the market in the early 1990s. The goal of these reviews is to ensure that the herbicide carries out its intended use without creating adverse side effects to humans and the environment. Since scientific methods are continually evolving and being developed, global regulatory agencies can require additional studies to address data gaps for pesticide renewals. During this reregistration process for rimsulfuron, a new confined rotational crop study was required to address a data gap requested by the European Food Safety Authority (EFSA). Consequently, the corresponding pyridine and pyrimidine radiolabeled [14C]rimsulfuron and [M + 3] stable isotopes of rimsulfuron were synthesized for this study to support the reregistration process.

Asbestos exposures associated with the use and handling of drilling mud additives.

This paper summarizes historical asbestos exposure data collected during the handling of short-fiber chrysotile asbestos that was used as an additive to drilling fluid in oil and gas exploration. A total of 1171 industrial hygiene (IH) personal and area air samples were collected and analyzed from more than 20 drilling rigs between 1972 and 1985. The dataset consists of 1097 short-term samples (<240min) with more than 80% having sample durations less than 30min. Average airborne fiber concentrations measured during asbestos handling activities ranged from 0.62 f/cc to 3.39 f/cc using phase-contrast microscopy (PCM). An additional 14 samples were considered long-term samples (>240min) and there were 60 samples with no reported sample duration. Eight-hour time-weighted average (8-h TWA) results, calculated using short-term samples, along with long-term samples greater than 240min, did not exceed contemporaneous Occupational Safety and Health Administration (OSHA) permissible exposure limits (PELs). This analysis fills a data gap in the evaluation of asbestos exposures from the use of drilling mud additives (DMAs) that contained chrysotile asbestos.

Breaking the Barriers: Machine-Learning-Based c-RASAR Approach for Accurate Blood-Brain Barrier Permeability Prediction.

The intricate nature of the blood-brain barrier (BBB) poses a significant challenge in predicting drug permeability, which is crucial for assessing central nervous system (CNS) drug efficacy and safety. This research utilizes an innovative approach, the classification read-across structure-activity relationship (c-RASAR) framework, that leverages machine learning (ML) to enhance the accuracy of BBB permeability predictions. The c-RASAR framework seamlessly integrates principles from both read-across and QSAR methodologies, underscoring the need to consider similarity-related aspects during the development of the c-RASAR model. It is crucial to note that the primary goal of this research is not to introduce yet another model for predicting BBB permeability but rather to showcase the refinement in predicting the BBB permeability of organic compounds through the introduction of a c-RASAR approach. This groundbreaking methodology aims to elevate the accuracy of assessing neuropharmacological implications and streamline the process of drug development. In this study, an ML-based c-RASAR linear discriminant analysis (LDA) model was developed using a dataset of 7807 compounds, encompassing both BBB-permeable and -nonpermeable substances sourced from the B3DB database (freely accessible from https://github.com/theochem/B3DB), for predicting BBB permeability in lead discovery for CNS drugs. The model's predictive capability was then validated using three external sets: one containing 276,518 natural products (NPs) from the LOTUS database (accessible from https://lotus.naturalproducts.net/download) for data gap filling, another comprising 13,002 drug-like/drug compounds from the DrugBank database (available from https://go.drugbank.com/), and a third set of 56 FDA-approved drugs to assess the model's reliability. Further diversifying the predictive arsenal, various other ML-based c-RASAR models were also developed for comparison purposes. The proposed c-RASAR framework emerged as a powerful tool for predicting BBB permeability. This research not only advances the understanding of molecular determinants influencing CNS drug permeability but also provides a versatile computational platform for the rapid assessment of diverse compounds, facilitating informed decision-making in drug development and design.

From past habitats to present threats: tracing North American weasel distributions through a century of climate and land use change

ContextShifts in climate and land use have dramatically reshaped ecosystems, impacting the distribution and status of wildlife populations. For many species, data gaps limit inference regarding population trends and links to environmental change. This deficiency hinders our ability to enact meaningful conservation measures to protect at risk species.ObjectivesWe investigated historical drivers of environmental niche change for three North American weasel species (American ermine, least weasel, and long-tailed weasel) to understand their response to environmental change.MethodsUsing species occurrence records and corresponding environmental data, we developed species-specific environmental niche models for the contiguous United States (1938–2021). We generated annual hindcasted predictions of the species’ environmental niche, assessing changes in distribution, area, and fragmentation in response to environmental change.ResultsWe identified a 54% decline in suitable habitat alongside high levels of fragmentation for least weasels and region-specific trends for American ermine and long-tailed weasels; declines in the West and increased suitability in the East. Climate and land use were important predictors of the environmental niche for all species. Changes in habitat amount and distribution reflected widespread land use changes over the past century while declines in southern and low-elevation areas are consistent with impacts from climatic change.ConclusionsOur models uncovered land use and climatic change as potential historic drivers of population change for North American weasels and provide a basis for management recommendations and targeted survey efforts. We identified potentially at-risk populations and a need for landscape-level planning to support weasel populations amid ongoing environmental changes.

Why do seismic hazard models worldwide appear to overpredict historical intensity observations?

Probabilistic seismic hazard assessments (PSHAs) provide the scientific basis for building codes to reduce damage from earthquakes. Despite their substantial impact, little is known about how well PSHA predicts actual shaking. Recent PSHA for California, Japan, Italy, Nepal, and France appear to consistently overpredict historically observed earthquake shaking intensities. Numerical simulations show that observed shaking is equally likely to be above or below predictions. This result from independently developed models and datasets in different countries and tectonic settings indicates possible systematic bias in the hazard models, the observations, or both. Analysis of possible causes shows that much of the discrepancy is due to a subtle and rarely considered issue: the conversion equations used in comparing the models-which forecast shaking as peak ground acceleration or velocity-and observations-parameterizations of qualitative shaking reports. Historical shaking reports fill a crucial data gap, but more research is warranted on how qualitative observations relate to instrumental shaking measures for earthquakes.

Challenges When Assessing Water-Related Environmental Impacts of Livestock Farming: A Case Study of a Cow Milk Production System in Catalonia

Water availability is a local issue of growing importance in Mediterranean areas where water scarcity linked to climate change and population growth is already leading to increased competition for this resource. This study is aimed at the following: (i) assessing the water-related environmental impacts (water use, freshwater ecotoxicity and eutrophication, marine eutrophication, acidification, human toxicity, and ionizing radiation) along the production chain of cow milk in Catalonia, northeastern Spain; and (ii) addressing the issues encountered (modelling choices, data gaps and inconsistencies) which t can affect the quality of results when performing a water-footprint comprehensive assessment, focusing on water use and associated water scarcity impacts. The scope included the process from the extraction of raw materials up to the distribution of the packaged fat- and protein-corrected milk to the distribution centres of the supermarket chains and markets. Results showed the farm stage to be determinant (contributing to over 60% of the impact), due to the impact of feed production. Impact results were in the range of the European benchmark given by the Product Environmental Footprint Category Rules for dairy products, except for the water scarcity footprint which was one order of magnitude larger than the reference value, due to water scarcity in Spain. Considering compound feed ingredients with a lower water scarcity footprint, and research into slurry treatment for its use as irrigation and cleaning water (without compromising safety and health) could help reduce this impact. Water accounting and traceability along the production chain could support the dairy industry to take responsibility for the consequences of their production choices.

Filling gaps in cloudy Landsat LST product by spatial-temporal fusion of multi-scale data

Land surface temperature (LST) is an important factor in studies of surface energy fluxes between the Earth's surface and atmosphere. The Landsat LST product has been applied widely due to its fine spatial resolution and high data quality. Frequent cloud coverage, however, results in different degrees of gaps in the Landsat LST images, restricting greatly their application in practical cases requiring continuous LST time-series. Gap filling is an important technique used to reconstruct the missing data in the Landsat LST images. Using only temporally neighboring data from the same sensor, however, current gap filling methods struggle to deal with large spatial gaps and large temporal changes in LST. To solve these challenging issues, in this paper, multi-scale data (i.e., the 2 km, all-sky, hourly GOES LST product) were proposed for gap filling of Landsat LST images, and a spatial-temporal random forest (STRF) method was developed. The GOES LST product can provide effective information on LST in the gaps of the target Landsat LST data, with great potential to decreasing the uncertainty in gap filling when large LST change exists or the gap size is large. Through experiments in six regions of the USA, the proposed STRF method was shown to be more accurate than three typical gap filling and spatio-temporal fusion methods, and particularly advantageous for cases involving large temporal changes or large spatial gaps in LST. Specifically, STRF produces an average root mean square error (RMSE) of 1.6444 K and average correlation coefficient (CC) of 0.8653 for the six regions, which are 0.1133 K smaller and 0.0176 larger than the most competitive benchmark method (i.e., the spatial random forest (SRF) method). Conceptually, by spatial-temporal fusion of multi-scale data in gap filling, STRF provides a new paradigm for both spatial-temporal fusion and gap filling. Furthermore, the proposed STRF has the potential to be applied to various gap filling tasks in other situations.