Previous Models Research Articles

Emerging Trends in Play-to-Earn (P2E) Games

This research aims to establish the primary drivers influencing the development and consumers’ decision-making process in web3 games—decentralized games that function according to the play-to-earn paradigm. We observe several types of micro-economies developed within five play-to-earn games and highlight four roles consumers play at any given time. Our study offers a different perspective on rational consumer behaviour in cryptocurrency-based games and paves the way to better understanding their dynamics and evolution. Results shed light on the construction of in-game economies and how individuals of a given type engage in different playing activities. Furthermore, we compare the key features of web3 games with those similar to classic online games and assess if the play-and-earn implementations represent an evolution from previous revenue models. Using our proposed methodology, researchers can compare and classify any P2E games. We conclude by establishing a set of actions that enable consumers to benefit from this new phenomenon.

Dose optimization of an adjuvanted peptide-based personalized neoantigen melanoma vaccine.

The advancements in next-generation sequencing have made it possible to effectively detect somatic mutations, which has led to the development of personalized neoantigen cancer vaccines that are tailored to the unique variants found in a patient's cancer. These vaccines can provide significant clinical benefit by leveraging the patient's immune response to eliminate malignant cells. However, determining the optimal vaccine dose for each patient is a challenge due to the heterogeneity of tumors. To address this challenge, we formulate a mathematical dose optimization problem based on a previous mathematical model that encompasses the immune response cascade produced by the vaccine in a patient. We propose an optimization approach to identify the optimal personalized vaccine doses, considering a fixed vaccination schedule, while simultaneously minimizing the overall number of tumor and activated T cells. To validate our approach, we perform in silico experiments on six real-world clinical trial patients with advanced melanoma. We compare the results of applying an optimal vaccine dose to those of a suboptimal dose (the dose used in the clinical trial and its deviations). Our simulations reveal that an optimal vaccine regimen of higher initial doses and lower final doses may lead to a reduction in tumor size for certain patients. Our mathematical dose optimization offers a promising approach to determining an optimal vaccine dose for each patient and improving clinical outcomes.

Intra-colony spatial variance of oxyregulation and hypoxic thresholds for key Acropora coral species.

Oxygen (O2) availability is essential for healthy coral reef functioning, yet how continued loss of dissolved O2 via ocean deoxygenation impacts performance of reef building corals remains unclear. Here, we examine how intra-colony spatial geometry of important Great Barrier Reef (GBR) coral species Acropora may influence variation in hypoxic thresholds for upregulation, to better understand capacity to tolerate future reductions in O2 availability. We first evaluate the application of more streamlined models used to parameterise Hypoxia Response Curve data, models that have been used historically to identify variable oxyregulatory capacity. Using closed-system respirometry to analyse O2 drawdown rate, we show that a two-parameter model returns similar outputs as previous 12th-order models for descriptive statistics such as the average oxyregulation capacity (Tpos) and the ambient O2 level at which the coral exerts maximum regulation effort (Pcmax), for diverse Acropora species. Following an experiment to evaluate whether stress induced by coral fragmentation for respirometry affected O2 drawdown rate, we subsequently identify differences in hypoxic response for the interior and exterior colony locations for the species Acropora abrotanoides, Acropora cf. microphthalma and Acropora elseyi. Average regulation capacity across species was greater (0.78-1.03 ± SE 0.08) at the colony interior compared with exterior (0.60-0.85 ± SE 0.08). Moreover, Pcmax occurred at relatively low pO2 of <30% (±1.24; SE) air saturation for all species, across the colony. When compared against ambient O2 availability, these factors corresponded to differences in mean intra-colony oxyregulation, suggesting that lower variation in dissolved O2 corresponds with higher capacity for oxyregulation. Collectively, our data show that intra-colony spatial variation affects coral oxyregulation hypoxic thresholds, potentially driving differences in Acropora oxyregulatory capacity.

Prognostic Value of the Modeled Prostate-Specific Antigen KELIM Confirmation in Metastatic Castration-Resistant Prostate Cancer Treated With Taxanes in FIRSTANA.

In a previous exploratory study, modeled early longitudinal prostate-specific antigen (PSA) kinetics observed within the 100-first treatment days with androgen deprivation therapy with or without docetaxel was associated with progression-free survival (PFS) and overall survival (OS) in patients with prostate cancer with rising PSA levels after primary local therapy. This prognostic value had to be confirmed in different settings. The objectives were to assess PSA kinetics modeling in patients with metastatic castration-resistant prostate cancer (mCRPC) treated with chemotherapy in FIRSTANA trial and to investigate modeled PSA kinetic parameters prognostic/predictive value. FIRSTANA phase III trial (ClinicalTrials.gov identifier: NCT01308567) assessed whether cabazitaxel is superior to docetaxel in terms of PFS/OS in patients with chemotherapy-naïve mCRPC. PSA longitudinal kinetics was assessed using the previous kinetic-pharmacodynamics model. Patient modeled ELIMination rate constant K (PSA.KELIM) was used to categorize favorable/unfavorable PSA declines (standardized PSA.KELIM < or ≥ 1.0 days-1) and further correlated with PFS/OS. In total, 1,050 of 1,168 enrolled patients were assessable for PSA.KELIM estimation. The median PSA.KELIM was 0.02 days-1. In univariate analyses, PSA.KELIM exhibited a significant prognostic value regarding survival: unfavorable versus favorable PSA.KELIM; median PFS, 3.6 months (95% CI, 3.0 to 4.2) versus 4.7 months (95% CI, 3.9 to 5.2), P = .002; median OS, 17.4 months (95% CI, 14.8 to 19.3) versus 28.4 months (95% CI, 26.7 to 31.6), P < .001. In multivariate analyses, PSA.KELIM was significant for PFS (hazard ratio [HR], 0.79 [95% CI, 0.67 to 0.93], P = .005) and OS (HR, 0.51 [95% CI, 0.44 to 0.60], P < .001), together with baseline radiological tumor progression and PSA doubling time. PSA.KELIM predictive value was not significant across treatment arms. This external validation study confirmed previous results about modeled PSA longitudinal kinetics prognostic value regarding PFS/OS in patients with mCRPC treated with taxanes. PSA.KELIM could be used to identify a subpopulation with poor prognosis, who may benefit from treatment intensification.

Radial Evolution of the Near-Sun Solar Wind: Parker Solar Probe Observations

Abstract A statistical study of the radial evolution of the solar wind within 0.3 au is shown in this Letter based on Parker Solar Probe observations. We show the radial distribution of the main solar wind parameters, including the solar wind speed V sw, magnetic field ∣B∣, the number density of electrons N e , protons N p , and α particles N α , and the temperature of protons T p and α particles T α . The power-law fitting results of these parameters in the near-Sun solar wind are compared with previous radial models. We also show the radial distribution of the angle between the magnetic field B , solar wind V sw, and radial vector R . In the solar wind within 0.3 au, θ BV sw , and θ BR mainly concentrate around 135°, and θ RV sw almost concentrates in the region less than 20°. Furthermore, we also present the radial distribution of the relative values between the solar wind parameters, including the electric neutrality estimation ((2 × N α + N p )/N e ≃ 1 within 0.2 au), relative number density ratio (N α /N p ≃ 0.02 in slow solar wind and N α /N p ≃ 0.04 in faster solar wind), relative temperature ratio (T α /T p decreases with the increase of heliocentric distance and its decay rate is larger in faster solar wind), and differential speed (both V α − V p and (V α − V p )/V A are larger in the faster solar wind and decrease as heliocentric distance increases).

Performance of machine-learning approach for prediction ofpre-eclampsia in a middle-income country.

Pre-eclampsia (PE) is a serious complication of pregnancy associated with maternal and fetal morbidity and mortality. As current prediction models have limitations and may not be applicable in resource-limited settings, we aimed to develop a machine-learning (ML) algorithm that offers a potential solution for developing accurate and efficient first-trimester prediction of PE. We conducted a prospective cohort study in Mexico City, Mexico to develop a first-trimester prediction model for preterm PE (pPE) using ML. Maternal characteristics and locally derived multiples of the median (MoM) values for mean arterial pressure, uterine artery pulsatility index and serum placental growth factor were used for variable selection. The dataset was split into training, validation and test sets. An elastic-net method was employed for predictor selection, and model performance was evaluated using area under the receiver-operating-characteristics curve (AUC) and detection rates (DR) at 10% false-positive rates (FPR). The final analysis included 3050 pregnant women, of whom 124 (4.07%) developed PE. The ML model showed good performance, with AUCs of 0.897, 0.963 and 0.778 for pPE, early-onset PE (ePE) and any type of PE (all-PE), respectively. The DRs at 10% FPR were 76.5%, 88.2% and 50.1% for pPE, ePE and all-PE, respectively. Our ML model demonstrated high accuracy in predicting pPE and ePE using first-trimester maternal characteristics and locally derived MoM. The model may provide an efficient and accessible tool for early prediction of PE, facilitating timely intervention and improved maternal and fetal outcome. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

X-Ray Polarimetry of the Dipping Accreting Neutron Star 4U 1624–49

We present the first X-ray polarimetric study of the dipping accreting neutron star 4U 1624−49 with the Imaging X-ray Polarimetry Explorer. We report a detection of polarization in the nondip time intervals with a confidence level of 99.99%. We find an average polarization degree (PD) of 3.1% ± 0.7% and a polarization angle of 81° ± 6° east of north in the 2–8 keV band. We report an upper limit on the PD of 22% during the X-ray dips with 95% confidence. The PD increases with energy, reaching from 3.0% ± 0.9% in the 4–6 keV band to 6% ± 2% in the 6–8 keV band. This indicates the polarization likely arises from Comptonization. The high PD observed is unlikely to be produced by Comptonization in the boundary layer or spreading layer alone. It can be produced by the addition of an extended geometrically thin slab corona covering part of the accretion disk, as assumed in previous models of dippers, and/or a reflection component from the accretion disk.

Implementation of deep neural networks learning on unmanned aerial vehicle based remote-sensing

Due to efficient and adaptable data collecting, unmanned aerial vehicle (UAV) has been a popular topic in computer vision (CV) and remote sensing (RS) in recent years. Inspiring by the recent success of deep learning (DL), several enhanced object identification and tracking methods have been broadly applied to a variety of UAV-related applications, including environmental monitoring, precision agriculture, and traffic management. In this research, we present efficient neural network (ENet), a unique deep neural network architecture designed exclusively for jobs demanding low latency operation. ENet is up to quicker, takes fewer floating-point operations per second (FLOPs), has fewer parameters, and offers accuracy comparable to or superior to that of previous models. We have tested it on the street and cityscapes reports on comparisons with current state-of-the-art approaches and the tradeoffs between a network's processing speed and accuracy. We give measurements of the proposed architecture's performance on embedded devices and offer software enhancements that might make ENet even quicker.

S3-Net: A Self-Supervised Dual-Stream Network for Radiology Report Generation.

Intelligent medicine is eager to automatically generate radiology reports to ease the tedious work of radiologists. Previous researches mainly focused on the text generation with encoder-decoder structure, while CNN networks for visual features ignored the long-range dependencies correlated with textual information. Besides, few studies exploit cross-modal mappings to promote radiology report generation. To alleviate the above problems, we propose a novel end-to-end radiology report generation model dubbed Self-Supervised dual-Stream Network (S3-Net). Specifically, a Dual-Stream Visual Feature Extractor (DSVFE) composed of ResNet and SwinTransformer is proposed to capture more abundant and effective visual features, where the former focuses on local response and the latter explores long-range dependencies. Then, we introduced the Fusion Alignment Module (FAM) to fuse the dual-stream visual features and facilitate alignment between visual features and text features. Furthermore, the Self-Supervised Learning with Mask(SSLM) is introduced to further enhance the visual feature representation ability. Experimental results on two mainstream radiology reporting datasets (IU X-ray and MIMIC-CXR) show that our proposed approach outperforms previous models in terms of language generation metrics.

A unified model of arithmetic with whole numbers, fractions, and decimals.

This article describes UMA (Unified Model of Arithmetic), a theory of children's arithmetic implemented as a computational model. UMA builds on FARRA (Fraction Arithmetic Reflects Rules and Associations; Braithwaite et al., 2017), a model of children's fraction arithmetic. Whereas FARRA-like all previous models of arithmetic-focused on arithmetic with only one type of number, UMA simulates arithmetic with whole numbers, fractions, and decimals. The model was trained on arithmetic problems from the first to sixth grade volumes of a math textbook series; its performance on tests administered at the end of each grade was compared to the performance of children in prior empirical research. In whole number arithmetic (Study 1), fraction arithmetic (Study 2), and decimal arithmetic (Study 3), UMA displayed types of errors, effects of problem features on error rates, and individual differences in strategy use that resembled those documented in the previous studies of children. Further, UMA generated correlations between individual differences in basic and advanced arithmetic skills similar to those observed in longitudinal studies of arithmetic development (Study 4). The results support UMA's main theoretical assumptions regarding arithmetic development: (a) most errors reflect small deviations from standard procedures via two mechanisms, overgeneralization and omission; (b) between-problem variations in error rates reflect effects of intrinsic difficulty and differential amounts of practice; and (c) individual differences in strategy use reflect underlying variation in parameters governing learning and decision making. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Population pharmacokinetics, enzyme occupancy, and pharmacodynamic modeling of soticlestat in patients with developmental and epileptic encephalopathies.

Soticlestat (TAK-935) is a first-in-class, selective inhibitor of cholesterol 24-hydroxylase (CH24H) under phase III development for the treatment of the developmental and epileptic encephalopathies (DEEs), Dravet syndrome (DS), and Lennox-Gastaut syndrome (LGS). A previous model characterized the pharmacokinetics (PKs), CH24H enzyme occupancy (EO), and pharmacodynamics (PDs) of soticlestat in healthy volunteers. The present study extended this original model for patients with DEEs and investigated sources of variability. Model-based simulations were carried out to optimize dosing strategies for use in clinical trials. Data from eight phase I and II trials of healthy volunteers or patients with DEEs receiving oral soticlestat 15-1350 mg were included, encompassing 218 individuals for population PK (PopPK) analyses and 306 individuals for PK/PD analyses. Dosing strategies were identified through model-based simulations. The final mixed-effect PopPK/EO/PD model consisted of a two-compartment PK model and an effect-site compartment in the PK/EO model; soticlestat concentrations at the effect site were linked to 24S-hydroxycholesterol plasma concentrations using a semimechanistic inhibitory indirect response model. Covariates were included to account for sources of variability. Pediatric dosing strategies were developed for four body weight bands (10 to <15, 15 to <30, 30 to <45, and 45-100 kg) to account for covariate effects by body weight. The final PopPK and PK/EO/PD models accurately described PK, EO, and PD profiles of soticlestat in healthy volunteers and patients with DEEs. Covariate analyses and model-based simulations facilitated optimization of phase III trial dosing strategies for patients with DS or LGS.

A simple prediction of time-mean and wave orbital velocities in submerged canopy

Flow within submerged canopies influences the transport of nutrients, sediment, pollutants, plant seeds and the settlement of larvae. To improve our understanding of mass transport within canopies, a simple model is proposed to predict the total time-varying velocity within submerged rigid canopies (representing coral reefs) and flexible canopies (representing seagrasses and saltmarshes). The model divides the momentum equations into a canopy layer and free-stream layer. The difference in the time derivative of the velocity between the two layers is balanced by the sum of the shear stress and canopy drag, both of which depend on the in-canopy total velocity. The present model extended the shear stress model developed for steady current to combined current and wave conditions without additional calibrating coefficients. The model agreed well with the in-canopy velocity measured in the present and several previous studies. Importantly, the proposed model significantly improved the accuracy of canopy time-mean velocity prediction, which reduced the root mean square error by more than 50 %, compared with previous models. The model revealed that the addition of waves can significantly decrease the in-canopy time-mean velocity.

Administrator Perspectives on the Impact of COVID-19 on the Administration of the Patient Driven Payment Model in U.S. Skilled Nursing Facilities.

The Patient Driven Payment Model (PDPM) was implemented in U.S. skilled nursing facilities (SNFs) in October 2019, shortly before COVID-19. This new payment model aimed to reimburse SNFs for patients' nursing needs rather than the previous model which reimbursed based on the volume of therapy received. Through 156 semi-structured interviews with 40 SNF administrators from July 2020 to December 2021, this qualitative study clarifies the impact of COVID-19 on the administration of PDPM at SNFs. Interview data were analyzed using modified grounded theory and thematic analysis. Our findings show that SNF administrators shifted focus from management of the PDPM to COVID-19-related delivery of care adaptations, staff shortfalls, and decreased admissions. As the pandemic abated, administrators re-focused their attention to PDPM. Policy makers should consider the continued impacts of the pandemic at SNFs, particularly on delivery of care, admissions, and staffing, on the ability of SNF administrators to administer a new payment model.

Interpreting drug synergy in breast cancer with deep learning using target-protein inhibition profiles

BackgroundBreast cancer is the most common malignancy among women worldwide. Despite advances in treating breast cancer over the past decades, drug resistance and adverse effects remain challenging. Recent therapeutic progress has shifted toward using drug combinations for better treatment efficiency. However, with a growing number of potential small-molecule cancer inhibitors, in silico strategies to predict pharmacological synergy before experimental trials are required to compensate for time and cost restrictions. Many deep learning models have been previously proposed to predict the synergistic effects of drug combinations with high performance. However, these models heavily relied on a large number of drug chemical structural fingerprints as their main features, which made model interpretation a challenge.ResultsThis study developed a deep neural network model that predicts synergy between small-molecule pairs based on their inhibitory activities against 13 selected key proteins. The synergy prediction model achieved a Pearson correlation coefficient between model predictions and experimental data of 0.63 across five breast cancer cell lines. BT-549 and MCF-7 achieved the highest correlation of 0.67 when considering individual cell lines. Despite achieving a moderate correlation compared to previous deep learning models, our model offers a distinctive advantage in terms of interpretability. Using the inhibitory activities against key protein targets as the main features allowed a straightforward interpretation of the model since the individual features had direct biological meaning. By tracing the synergistic interactions of compounds through their target proteins, we gained insights into the patterns our model recognized as indicative of synergistic effects.ConclusionsThe framework employed in the present study lays the groundwork for future advancements, especially in model interpretation. By combining deep learning techniques and target-specific models, this study shed light on potential patterns of target-protein inhibition profiles that could be exploited in breast cancer treatment.

Superblock Design and Evaluation by a Microscopic Door-to-Door Simulation Approach

The present study contributes to narrowing down the research gap in modeling individual door-to-door trips in a superblock scenario and in evaluating the respective impacts in terms of travel times, modal shifts, traffic performance, and environmental benefits. The methods used are a multiple-criteria approach to identify the superblocks and a large-scale, multi-model, activity-based microscopic simulation. These methods were applied to the city of Bologna, Italy, where 49 feasible superblocks were identified. A previous large-scale microscopic traffic model of Bologna is leveraged to build a baseline scenario. A superblock scenario is then created to model five proposed traffic intervention measures. Several mobility benefit indicators at both citywide and superblock levels are compared. The simulation results indicate a significant increase in walking time for car drivers, while the average waiting time of bus users decreases due to the increased frequency of bus services. This leads to a noticeable car-to-bus shift. In addition, absolute traffic volumes and traffic-related emissions decreased significantly. Surprisingly, traffic volumes on the roads around the superblocks did not increase as expected. In general, this research provides scientists and urban and transport planners with insights into how changes in door-to-door travel times of multi-modal trips can impact individual travel behavior and traffic performance at a citywide level. However, the study still has limitations in modeling the long-term effects regarding changing activity locations within the superblocks.

Experimental Hydrothermal Alteration of Rhyolite and Andesite at 325 °C and 300 Bar: Implications for a Potential Role of Volcanic Glass in the Fluid Composition in the Okinawa Trough

The experimental study of water–rock reactions under high-temperature and -pressure conditions is a useful approach to constrain controlling factors of the fluid composition in a natural hydrothermal system. Previous studies have focused mainly on the mid-ocean ridge fields, and the hydrothermal alteration of intermediate-to-felsic rocks has been less emphasized despite its potential importance in the fluid chemistry in an arc/back-arc basin setting. We examined the alteration processes of fresh rhyolite and andesite rocks collected from the middle and southern Okinawa Trough, respectively, at 325 °C and 300 bar (the estimated condition at the reaction zone in the fields), especially focusing on the behavior of silica between the solid and liquid phases. The experimental fluids are characterized by the high Si concentration up to 30 mM, indicating the substantial dissolution of volcanic glass in the analyzed rocks. The high Si concentration in the fluids was presumably buffered by amorphous silica, precipitated from the fluids as a precursor of hydrothermal quartz, during the experiments. Our results emphasize a previously overlooked role of volcanic glass/amorphous silica in the fluid composition in the Okinawa Trough and are consistent with the previous model of pumice replacement mineralization for the SMS deposit formation in the trough.

Modeling the persistence of Opisthorchis viverrini worm burden after mass-drug administration and education campaigns with systematic adherence.

Opisthorchis viverrini is a parasitic liver fluke contracted by consumption of raw fish, which affects over 10 million people in Southeast Asia despite sustained control efforts. Chronic infections are a risk factor for the often fatal bile duct cancer, cholangiocarcinoma. Previous modeling predicted rapid elimination of O. viverrini following yearly mass drug administration (MDA) campaigns. However, field data collected in affected populations shows persistence of infection, including heavy worm burden, after many years of repeated interventions. A plausible explanation for this observation is systematic adherence of individuals in health campaigns, such as MDA and education, with some individuals consistently missing treatment. We developed an agent-based model of O. viverrini which allows us to introduce various heterogeneities including systematic adherence to MDA and education campaigns at the individual level. We validate the agent-based model by comparing it to a previously published population-based model. We estimate the degree of systematic adherence to MDA and education campaigns indirectly, using epidemiological data collected in Lao PDR before and after 5 years of repeated MDA, education and sanitation improvement campaigns. We predict the impact of interventions deployed singly and in combination, with and without the estimated systematic adherence. We show how systematic adherence can substantially increase the time required to achieve reductions in worm burden. However, we predict that yearly MDA campaigns alone can result in a strong reduction of moderate and heavy worm burden, even under systematic adherence. We predict latrines and education campaigns to be particularly important for the reduction in overall prevalence, and therefore, ultimately, elimination. Our findings show how systematic adherence can explain the observed persistence of worm burden; while emphasizing the benefit of interventions for the entire population, even under systematic adherence. At the same time, the results highlight the substantial opportunity to further reduce worm burden if patterns of systematic adherence can be overcome.

Three-stage modeling of HIV infection and implications for antiretroviral therapy.

We consider a deterministic model of HIV infection that involves macrophages as a long-term active reservoir to describe all three stages of the disease process: the acute stage, chronic infection, and the transition to AIDS. The proposed model is shown to retain crucial properties, such as the positivity of solutions, regardless of variations in model parameters. A dynamical analysis is performed to identify the local stability properties of the viral clearance steady state. This analysis illustrates how chronically infected macrophages can explain the progression to AIDS and provoke viral explosion, while previous models do not. We further demonstrate that the infected T-cell population, even if not responsible for the majority of new infections that lead to viral explosion, may contribute significantly to the transition amongst the three stages of infection. Moreover, we explore the implications of the model for the administration of antiretroviral therapy (ART) and provide quantitative estimates that emphasize the time sensitive nature of treatment initiation and the level of drug efficacy. Finally, we study the effects of treatment interruption on the disease dynamics predicted by the model and elucidate the influence of both interruption time and duration.

Adjoint Waveform Tomography for Crustal and Upper Mantle Structure of the Middle East and Southwest Asia for Improved Waveform Simulations Using Openly Available Broadband Data

ABSTRACT We present a new model of radially anisotropic seismic wavespeeds for the crust and upper mantle of a broad region of the Middle East and Southwest Asia (MESWA) derived from adjoint waveform tomography. The new model enables fully 3D simulations of complete three-component waveforms and provides improved fits that were not possible with previous models. We inverted over 32,000 waveforms from 192 earthquakes recorded by over 1000 openly available broadband seismic stations from permanent and temporary networks in the region with highly uneven coverage. Inversion iterations proceeded from the period band 50–100 s in six stages and 54 total iterations reducing the minimum period to 30 s. Our final model, MESWA, improves waveform fits compared to the starting and other models for both the data used in the inversion and an independent validation set of 66 events. Restitution tests indicate that the model resolves features in the central part of the model to depths of about 150 km. The new model reveals tectonic features imaged by other studies and methods but in a new holistic model of anisotropic shear and compressional wavespeeds (VS and VP, respectively) covering a larger domain with smaller scale length and amplified features. Examples include low crustal VS in the Tethyan belt and low mantle VS following divergent (Gulf of Aden, Red Sea) and transform (Dead Sea fault) margins of the Arabian plate. Low VS is imaged below Cenozoic volcanic centers of the Mecca–Madina–Nafud Line, Arabian Peninsula, and the Türkiye–Iran border region. Elevated VS tracks Makran subduction under southeast Iran with near vertical dip. MESWA could be used as a starting model for further improvements, say, using waveforms from in-country seismic networks that are not currently openly available and/or smaller-scale studies targeting a shorter period. The model could be used to improve earthquake hazard studies and nuclear explosion monitoring.

Identifying Spatial Determinants of Rice Yields in Main Producing Areas of China Using Geospatial Machine Learning

Rice yield is essential to global food security under increasingly frequent and severe climate change events. Spatial analysis of rice yields becomes more critical for regional action to ensure yields and reduce climate impacts. However, the understanding of the spatially varied geographical, climate, soil, and environmental factors of rice yields needs to be improved, leading to potentially biased local rice yield prediction and responses to climate change. This study develops a spatial machine learning-based approach that integrates machine learning and spatial stratified heterogeneity models to identify the determinants and spatial interactions of rice yields in the main rice-producing areas of China, the world’s largest rice-producing nation. A series of satellite remote sensing-derived variables are collected to characterize varied geographical, climate, soil, and environmental conditions and explain the spatial disparities of rice yields. The first step is to explore the spatial clustering patterns of the rice yield distributions using spatially global and local autocorrelation models. Next, a Geographically Optimal Zones-based Heterogeneity (GOZH) model, which integrates spatial stratified heterogeneity models and machine learning, is employed to explore the power of determinants (PD) of individual spatial variables in influencing the spatial disparities of rice yields. Third, geographically optimal zones are identified with the machine learning-derived optimal spatial overlay of multiple geographical variables. Finally, the overall PD of various variables affecting rice yield distributions is calculated using the multiple variables-determined geographically optimal zones and the GOZH model. The comparison between the developed spatial machine learning-based approach and previous related models demonstrates that the GOZH model is an effective and robust approach for identifying the spatial determinants and their spatial interactions with rice yields. The identified spatial determinants and their interactions are essential for enhancing regional agricultural management practices and optimizing resource allocation within diverse main rice-producing regions. The comprehensive understanding of the spatial determinants and heterogeneity of rice yields of this study has a broad impact on agricultural strategies and food security.