Mapping Model Research Articles

Spatio-temporal characterization of phenotypic resistance in malaria vector species.

Malaria, a deadly disease caused by Plasmodium protozoa parasite and transmitted through bites of infected female Anopheles mosquitoes, remains a significant public health challenge in sub-Saharan Africa. Efforts to eliminate malaria have increasingly focused on vector control using insecticides. However, the emergence of insecticide resistance (IR) in malaria vectors pose a formidable obstacle, and the current IR mapping models remain static, relying on fixed coefficients. This study introduces a dynamic spatio-temporal approach to characterize phenotypic resistance in Anopheles gambiae complex and Anopheles arabiensis. We developed a cellular automata (CA) model and applied it to data collected from Ethiopia, Nigeria, Cameroon, Chad, and Burkina Faso. The data encompasses georeferenced records detailing IR levels in mosquito vector populations across various classes of insecticides. In characterizing the dynamic patterns of confirmed resistance, we identified key driving factors through correlation analysis, chi-square tests, and extensive literature review. The CA model demonstrated robustness in capturing the spatio-temporal dynamics of confirmed IR states in the vector populations. In our model, the key driving factors included insecticide usage, agricultural activities, human population density, Land Use and Land Cover (LULC) characteristics, and environmental variables. The CA model developed offers a robust tool for countries that have limited data on confirmed IR in malaria vectors. The embrace of a dynamical modeling approach and accounting for evolving conditions and influences, contribute to deeper understanding of IR dynamics, and can inform effective strategies for malaria vector control, and prevention in regions facing this critical health challenge.

Optimization Study of Soil Organic Matter Mapping Model in Complex Terrain Areas: A Case Study of Mingguang City, China

Traditional soil organic matter mapping is mostly polygonal drawing, which is even more difficult to accurately depict in complex terrain areas. The spatial distribution of soil organic matter is closely related to agricultural production, natural resources, environmental governance, and socio-economic development. Efficiently, economically, and accurately obtaining information on changes in soil organic matter in areas with diverse topography is an urgent problem to be solved. Mingguang City has a high research value because of its unique topography and natural landscape. To solve the problem of soil organic matter mapping in this area, this study will construct an excellent organic matter prediction model. Using 173 soil survey samples (123 for training and 50 for testing), the optimal feature variable subsets selected from 31 environmental variables through Pearson correlation, stepwise regression-variance inflation factor, and recursive feature elimination models based on different algorithms were employed. Each selected feature subset was then used to construct organic matter prediction models using multiple advanced machine learning algorithms. By comparing accuracy validation and model performance, the organic matter prediction model suitable for Mingguang City (RFE-RF_SVM) was obtained, that is, the prediction model of organic matter based on support vector machines with the feature variables screened by the feature recursive elimination algorithm of random forest with RMSE = 3.504, VSI = 0.036, and R-squared = 0.730. Furthermore, the analysis focused on assessing the significance of the predictive factors. The mapping results of this study show that the soil organic matter content in the central and northwestern parts of the study area is low, and the reasons for this situation are different. The central part is mainly caused by the change of land use and topography, while the northwestern part is caused by the loose soil structure caused by the parent material. The government can take targeted measures to improve the soil in the areas with poor organic matter.

A Prototype Software Framework for Transferable Computational Health Economic Models and Its Early Application in Youth Mental Health.

We are developing an economic model to explore multiple topics in Australian youth mental health policy. To help make that model more readily transferable to other jurisdictions, we developed a software framework for authoring modular computational health economic models (CHEMs) (the software files that implement health economic models). We specified framework user requirements for: a simple programming syntax; a template CHEM module; tools for authoring new CHEM modules; search tools for finding existing CHEM modules; tools for supplying CHEM modules with data; reproducible analysis and reporting tools; and tools to help maintain a CHEM project website. We implemented the framework as six development version code libraries in the programming language R that integrate with online services for software development and research data archiving. We used the framework to author five development version R libraries of CHEM modules focussed on utility mapping in youth mental health. These modules provide tools for variable validation, dataset description, multi-attribute instrument scoring, construction of mapping models, reporting of mapping studies and making out of sample predictions. We assessed these CHEM module libraries as mostly meeting transparency, reusability and updatability criteria that we have previously developed, but requiring more detailed documentation and unit testing of individual modules. Our software framework has potential value as a prototype for future tools to support the development of transferable CHEMs.Code: Visit https://www.ready4-dev.com for more information about how to find, install and apply the prototype software framework.

Efficiency Map Model for PMSM to Use in EV Simulation

As the automotive industry continues to transition towards sustainable solutions, Electric Vehicles (EVs) have emerged as a promising alternative. Central to the performance of EVs is the efficiency of their propulsion systems, particularly Permanent Magnet Synchronous Motors (PMSM). This research paper presents the development and implementation of an Efficiency Map Model tailored for PMSMs, aiming to enhance the accuracy of EV simulation studies. The implications of this research extend beyond academia, providing valuable guidance for automotive engineers, electric vehicle manufacturers, and policymakers involved in the development and deployment of sustainable transportation solutions. The proposed Efficiency Map Model contributes to the ongoing efforts to enhance the accuracy of EV simulations, fostering the design and implementation of more energy-efficient and environmentally friendly transportation systems. Keywords— Motor Efficiency, Permanent Magnet Synchronous Motors (PMSM), Design Parameters, Simulation, Efficiency Map Model

A support vector machine model of landslide susceptibility mapping based on hyperparameter optimization using the Bayesian algorithm: a case study of the highways in the southern Qinghai–Tibet Plateau

A support vector machine model of landslide susceptibility mapping based on hyperparameter optimization using the Bayesian algorithm: a case study of the highways in the southern Qinghai–Tibet Plateau

Research on compensation method for starlight emission accuracy based on star point focal length traversal

Star simulators are essential equipment for ground calibration of star sensors and are widely used in the aerospace field. Aiming at the problem that it is difficult to further improve the emission accuracy of the current star simulator due to the lack of comprehensive analysis of the factors affecting the error, a comprehensive error transfer model consisting of star point position deviation, principal point position deviation, focal length deviation, distortion deviation, and object plane tilt deviation was established. Analyzed the design basis for distortion tolerance of the optical system of the star simulator, and the required distortion tolerance for a 0–30° field of view with starlight emission accuracy better than 5″, 10″, and 20″ was determined. A mapping model between star point position and starlight emission accuracy has been established, and a compensation method for starlight emission accuracy based on star point focal length traversal has been proposed. Taking field of view of Φ20° and theoretical starlight emission accuracy better than 16″ as an example, a stellar simulation optical system has been designed, on this basis, an experimental platform was built and compared with existing unified focal length compensation and star map region partition compensation methods, verifying the performance of the starlight emission accuracy compensation method based on comprehensive focal length. The experimental results show that the maximum error of uncorrected starlight emission accuracy is 82.14". After three corrections using the unified focal length compensation method, the starlight emission accuracy is 15.27". Using the compensation method of star map region partition to achieve a starlight emission accuracy of 13.39". The starlight emission accuracy compensation method based on star point focal length traversal is used after one correction, achieve a starlight emission accuracy of 11.23″, The proposed method is superior to existing methods in terms of difficulty and accuracy in correction, and can provide new research ideas and advanced technical means for the development of high-precision star simulators.

Multiphase photoclinometry as applied to the lunar photometry with LROC NAC data

An original method for photometric and geometric correction of LROC NAC data with high resolution (up to 0.5 m/pix) has been developed. The technique is based on photogrammetry and multiphase photoclinometry and allows us to obtain a longitudinal slope map and digital elevation model (DEM) with the resolution of LROC NAC CDR input images as well as to map parameters of model phase function. Obtained DEMs, requiring only LROC NAC images and LRO SPICE-kernels, exhibit significantly fewer defects and artifacts compared to existing DEMs, because they are derived from the same images they correct (self-orthorectification).This method was used to study the area of the photometric anomaly, the Irregular Mare Patch (IMP) formation Ina. A zoning map of the correlation diagram of phase ratio vs. equigonal albedo shows significant differences in the optical (photometric) properties of the regolith for hummocky and blocky formations of the IMP Ina, compared to the surrounding areas, which indicates the different nature of their formation, age, and surface roughness, contradicting some models of the IMP formation. The analysis reveals the incompleteness or inconsistencies of previously proposed models of the IMP's formation mechanisms. The high-quality DEM of the Ina formation and surrounding area with a resolution of 0.5 m/pixel was constructed.

An online prediction and compensation method for robot position errors embedded with error-motion correlation

Error prediction and compensation are crucial requirements for improving robot accuracy. To this end, this paper introduces an advanced online method that integrates error-motion correlation for the precise prediction and compensation of robot position errors. The proposed method includes feature selection, model interpretability design, and compensation value smoothness. Analyzing the error characteristics and designing a model based on error-motion correlation reveals that the proposed method reduces position errors by 92 % and 89 % at a frequency of 250 Hz in two tasks with different working conditions. This reduction in position errors ensures smoother compensation, leading to a notable improvement in accuracy for high-precision robotics applications. Unlike existing research that focuses on mapping models, the proposed method prioritizes understanding error behavior, thereby resulting in a comprehensive approach for error management in robotic systems. This contribution is invaluable for advancing the field of precision robotics and ensuring reliable performances in various robotic tasks.

A Scene Unmixing Deep Learning Network for Local Climate Zone Mapping and Analysis Using Very High Resolution Remote Sensing Imagery

Abstract. With the acceleration of urbanization, the environment and climate necessary for our survival have gradually deteriorated, leading to the increasing prominence of the Urban Heat Island (UHI) effect. Local Climate Zone (LCZ) classification, as a standard of urban morphology, has become an essential tool for monitoring the UHI effect and conducting temperature studies. Deep Learning (DL) models have the ability to represent high-level semantic features. Therefore, this paper proposes amixed scene unmixing DL framework for LCZ mapping and analysis using Very High Resolution (VHR) remote sensing images. This framework consists of a two-stream deep network, including a pure scene classification network (PS-Net) and a mixed scene unmixing network (MSU-Net). We conducted random sampling tests in Wuhan, China in the experiment A. The results show that this model achieved a satisfactory accuracy with the Overall Accuracies (OAs) is 96.78% and a mixed scene unmixing Mean Absolute Error (MAE) of 0.0495. Furthermore, we applied the proposed model to generate LCZ map for five districts in Wuhan in the experiment B. The test accuracy between two experiments differs very slightly. These results demonstrate the applicability and potential of our model for LCZ mapping and urban climate analysis.

IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning

We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we incorporate the bottleneck by a confidence-aware encoder, which encodes inputs into latent representations according to the confidence of the input data belonging to the region where training data is located, and utilize a Gaussian decoder to predict means and variances of outputs conditional on representation variables. Furthermore, we propose a data augmentation based information bottleneck objective which can enhance the quantification quality of the extrapolation uncertainty, and the encoder and decoder can be both trained by minimizing a tractable variational bound of the objective. In comparison to uncertainty quantification (UQ) methods for scientific learning tasks that rely on Bayesian neural networks with Hamiltonian Monte Carlo posterior estimators, the model we propose is computationally efficient, particularly when dealing with large-scale datasets. The effectiveness of the IB-UQ model has been demonstrated through several representative examples, such as regression for discontinuous functions, learning nonlinear operators for partial differential equations, and a large-scale climate map model. The experimental results indicate that the IB-UQ model can handle noisy data, generate robust predictions, and provide confident uncertainty evaluation for out-of-distribution data.

Georeferencing of Satellite Images with Geocoded Image Features

Abstract. Currently, using digital orthophoto map (DOM) and digital elevation model (DEM) as reference to achieve geometric positioning of newly acquired satellite images has become a popular photogrammetric approach. However, this method relies on DOM and DEM data which requires a lot of storage space in practical applications. In addition, for geometric positioning of satellite images, only sparse image feature points are needed as control points. Consequently, for the sake of convenience, the compression of control data emerges as a necessity with significant practical implications. This paper investigates a "cloud control" photogrammetry method based on geocoded image features. The method extracts SIFT feature points from DOMs, and obtains their ground coordinates, then constructs geocoded image feature library instead of DOM and DEM data as control, thus realizing the compression of control data. Experiments conducted on the Tianhui-1, Ziyuan-3 and Gaofen-2 satellite images demonstrate that the proposed method can achieve high-precision geometric positioning of satellite images and greatly reduce the size of the control data. Specifically, with the reduction of the reference data from 180~1248 MB 2 m DOM and 30 m DEM to 5~10 MB geocoded image features, the geopositional accuracies of the test Tianhui-1, Ziyuan-3 and Gaofen-2 images are improved from 3.12 pixels to 1.74 pixels, 3.69 pixels to 1.09 pixels, and 150.93 pixels to 2.67 pixels, respectively.

Joint estimation of PM2.5 and O3 concentrations using a hybrid model in Beijing-Tianjin-Hebei, China

The distribution data of fine particulate matter (PM2.5) and ozone (O3) concentrations at high spatiotemporal resolutions play a pivotal role in monitoring and collectively combating atmospheric PM2.5 and O3 pollution, thereby enhancing the quality of human habitation environments. This study integrates reanalysis, satellite observations, and ground-level monitoring data to develop a GLMM-DF (generalized linear mixed effects model-deep forest) hybrid model for joint estimation of PM2.5 and O3 concentrations in the Beijing-Tianjin-Hebei region. The model effectively considers the spatiotemporal heterogeneity inherent in PM2.5 and O3 and their nonlinear relationships with the estimating variables. The cross-validation results indicate that the GLMM-DF model exhibits high estimation accuracy. For PM2.5 estimation, the coefficient of determination (R2), mean absolute error (MAE), and root mean square Error (RMSE) are 0.949, 5.81 μg m−3, and 9.42 μg m−3, respectively. Regarding O3 estimation, the R2, MAE, and RMSE are 0.966, 7.77 μg m−3, and 11.82 μg m−3, respectively. Furthermore, the model demonstrates favorable spatiotemporal performance, with the PM2.5-O3 interaction contributing to enhancing model performance. Utilizing this model for mapping, we analyzed the spatiotemporal trends of PM2.5 and O3 in the Beijing-Tianjin-Hebei region, uncovering several intriguing phenomena.

The Influence of the Mind Mapping Model on Students’ Learning Outcomes in Biology Learning at Class XI in Tumou Tou Christian High School, Bitung City

Based on the results of observations and interviews with class This research aims to find out whether the mind mapping model can improve student learning outcomes in plant tissue material in class XI Tumou Tou Christian High School. This research uses a quasi-experimental method (quasi-experiment). The subjects of this research were class XI-A as the experimental class and class XI-C as the control class. Both classes will be given learning outcomes tests in the form of pretest and posttest. Based on the results of data analysis, the results showed that there was an influence of the mind mapping model on student learning outcomes in plant tissue material in class XI Tumou Tou Christian High School. This is based on the results of the t test using IBM SPSS for Windows if the Sig. (2-tailed) < Research Alpha (0.05), namely 0.00 <0.05, then H0 is rejected and H1 is accepted. This shows that there is an influence of applying the mind mapping model on improving student learning outcomes in plant tissue material in class XI Tumou Tou Christian High School.

Urban flood susceptibility mapping using remote sensing, social sensing and an ensemble machine learning model

Flood susceptibility mapping is crucial for urban disaster management. However, the heterogeneity of urban land use and the complexity of terrain pose challenges to the accuracy and generalizability of flood models. In this paper, we propose a framework named the EMF model for urban flood mapping. Specifically, the social sensing and remote sensing were used for flooding information collection. The XGBoost, Support Vector Classifier (SVC), Multilayer Perceptron (MLP), and Multimodal Deep Learning (MDL), were used as the predictive models, and their results were ensembled using a Random Forest model to produce the final outcome. Results show that the EMF model outperforms the standalone models, with an accuracy of 0.942 on the training set and 0.940 on the testing set. The accuracy of the five models is ranked as EMF > MDL > XGBoost > SVC > MLP. The flood map indicates that flooding has a greater impact on the outskirts and suburbs of the city compared to its central urban areas. Farmland is the most affected land type, making up 54.8 % of the flooded area. Overall, the proposed framework enables rapid and accurate identification of flood-prone areas, providing technical support for managers in formulating effective flood prevention strategies.

Learning spectral-indices-fused deep models for time-series land use and land cover mapping in cloud-prone areas: The case of Pearl River Delta

Mapping of highly dynamic changes in land use and land cover (LULC) can be hindered by various cloudy conditions with optical satellite images. These conditions result in discontinuities in high-temporal-density LULC mapping. In this paper, we developed an integrated time series mapping method to enhance the LULC mapping accuracy and frequency in cloud-prone areas by incorporating spectral-indices-fused deep models and time series reconstruction techniques. The proposed method first reconstructed cloud-contaminated pixels through time series filtering, during which the cloud masks initialized by a deep model were refined and updated during the reconstruction process. Then, the reconstructed time series images were fed into a spectral-indices-fused deep model trained on samples collected worldwide for classification. Finally, post-classification processing, including spatio-temporal majority filtering and time series refinement considering land–water interactions, was conducted to enhance the LULC mapping accuracy and consistency. We applied the proposed method to the cloud- and rain-prone Pearl River Delta (i.e., Guangdong–Hong Kong–Macao Greater Bay Area, GBA) and used time series Sentinel-2 images as the experimental data. The proposed method enabled seamless LULC mapping at a temporal frequency of 2–5 days, and the production of 10 m resolution annual LULC products in the GBA. The assessment yielded a mean overall accuracy of 87.01% for annual mapping in the four consecutive years of 2019–2022 and outperformed existing mainstream LULC products, including ESA WorldCover (83.98%), Esri Land Cover (85.26%), and Google Dynamic World (85.06%). Our assessment also reveals significant variations in LULC mapping accuracies with different cloud masks, thus underscoring their critical role in time series LULC mapping. The proposed method has the potential to generate seamless and near real-time maps for other regions in the world by using deep models trained on datasets collected globally. This method can provide high-quality LULC data sets at different time intervals for various land and water dynamics in cloud- and rain-prone regions. Notwithstanding the difficulties of obtaining high-quality LULC maps in cloud-prone areas, this paper provides a novel approach for the mapping of LULC dynamics and the provision of reliable annual LULC products.

Prediction of hourly wind speed time series at unsampled locations using machine learning

Various models for wind speed mapping have been developed, with increasing attention on models focusing on mapping wind speed distribution. This study extends these models to predict hourly wind speed time series at unsampled locations. A model based on the quantile mapping (QM) procedure was compared to a traditional and machine-learning model to interpolate wind speed spatially. These proposed models were also used with inputs from the ERA5 reanalysis dataset, enabling them to consider local variation in orography and large-scale wind fields. A widely used procedure for mean bias correction of reanalysis based on the Global Wind Atlas (GWA) was implemented and compared to the proposed models. It was found that the QM and machine learning model, both using input from ERA5, significantly outperformed GWA bias correction in terms of time series correlation and probability distribution. Despite being more computationally intensive than GWA bias correction, both models are recommended due to their significantly (in a statistical sense) superior performance.

A Multinational, Multicenter Study Mapping Models of Kidney Supportive Care Practice

IntroductionKidney supportive care (KSC) integrates kidney and palliative care to improve quality of life for people with chronic kidney disease. Despite increasing interest and global advocacy to integrate KSC into kidney care, evidence to guide optimal care delivery is limited. MethodsThis observational cross-sectional study used an online survey to describe current KSC models in Australia, Aotearoa-New Zealand and the United Kingdom (UK). ResultsBetween April and December 2022, 114 units responded (response rate 67%), with 66% having a dedicated KSC service (UK 74%, Australia 58%, New Zealand 67%). Many different healthcare professionals worked in KSC services with diversity in clinical resources and activities between units and across countries. Overall, funding for KSC services was low, with a median full time equivalent per unit (standardised per 100 people receiving haemodialysis) of 0.51 (interquartile range 0.17-1.05) and 4 units provided a service without allocated funding. The scope of KSC service was wide-ranging and prioritised activities included symptom management, psychological support, complex future treatment planning and discussion, and care coordination. There were no significant differences between countries in terms of location of care provision, frequency of review, referral patterns or discharge rates, but there was variation described within countries. ConclusionModels of KSC vary markedly across kidney units and between countries. Despite this variation there was consistency in terms of clinical priorities which were person-centred and focused on physical and psychosocial wellbeing. Further research is required to evaluate the effectiveness of KSC provision, alongside improved funding methods to ensure sustainable and equitable KSC delivery.

PQSDC: a parallel lossless compressor for quality scores data via sequences partition and run-length prediction mapping.

The quality scores data (QSD) account for 70% in compressed FastQ files obtained from the short and long reads sequencing technologies. Designing effective compressors for QSD that counterbalance compression ratio, time cost, and memory consumption is essential in scenarios such as large-scale genomics data sharing and long-term data backup. This study presents a novel parallel lossless QSD-dedicated compression algorithm named PQSDC, which fulfills the above requirements well. PQSDC is based on two core components: a parallel sequences-partition model designed to reduce peak memory consumption and time cost during compression and decompression processes, as well as a parallel four-level run-length prediction mapping model to enhance compression ratio. Besides, the PQSDC algorithm is also designed to be highly concurrent using multicore CPU clusters. We evaluate PQSDC and four state-of-the-art compression algorithms on 27 real-world datasets, including 61.857 billion QSD characters and 632.908 million QSD sequences. (1) For short reads, compared to baselines, the maximum improvement of PQSDC reaches 7.06% in average compression ratio, and 8.01% in weighted average compression ratio. During compression and decompression, the maximum total time savings of PQSDC are 79.96% and 84.56%, respectively; the maximum average memory savings are 68.34% and 77.63%, respectively. (2) For long reads, the maximum improvement of PQSDC reaches 12.51% and 13.42% in average and weighted average compression ratio, respectively. The maximum total time savings during compression and decompression are 53.51% and 72.53%, respectively; the maximum average memory savings are 19.44% and 17.42%, respectively. (3) Furthermore, PQSDC ranks second in compression robustness among the tested algorithms, indicating that it is less affected by the probability distribution of the QSD collections. Overall, our work provides a promising solution for QSD parallel compression, which balances storage cost, time consumption, and memory occupation primely. The proposed PQSDC compressor can be downloaded from https://github.com/fahaihi/PQSDC.

‘Conga lines’ of Ediacaran fronds: insights into the reproductive biology of early metazoans

Late Ediacaran strata from Newfoundland, Canada (~574–560 Ma) document near-census palaeocommunities of some of the earliest metazoans. Such preservation enables reproductive strategies to be inferred from the spatial distribution of populations of fossilized benthic organisms, previously revealing the existence of both propagule and stoloniferous reproductive modes among Ediacaran frondose taxa. Here, we describe ‘conga lines’: linear arrangements of more than three closely spaced fossil specimens. We calculate probabilistic models of point maps of 13 fossil-bearing bedding surfaces and show that four surfaces contain conga lines that are not the result of chance alignments. We then test whether these features could result from passive pelagic propagules settling in the lee of an existing frond, using computational fluid dynamics and discrete phase modelling. Under Ediacaran palaeoenvironmental conditions, preferential leeside settlement at the spatial scale of the conga lines is unlikely. We therefore conclude that these features are novel and do not reflect previously described reproductive strategies employed by Ediacaran organisms, suggesting the use of mixed reproductive strategies in the earliest animals. Such strategies enabled Ediacaran frondose taxa to act as reproductive generalists and may be an important facet of early metazoan evolution.

Quantifying aboveground biomass, soil organic carbon and erosion with a detailed crop map and PESERA model in the Yangtze River Basin

AbstractSoil erosion represents a primary threat to soil systems with adverse implications for ecosystem services, crop production, potable water and carbon storage. While numerous studies have quantified the spatial distribution of aboveground Biomass (AGB), soil erosion and soil organic carbon (SOC) in the Yangtze River Basin (YRB), limited attention has been given to assessing the contributions of different land use types and especially crop types to AGB, soil erosion and SOC. In most studies, cropland is taken as a land use class, while detailed crop types and rotation patterns, and their effect on soil erosion and SOC, vary significantly. In this study, we used the Metronamica model to generate a detailed crop rotation and distribution map across the YRB and subsequently employed the Pan‐European Soil Erosion Risk Assessment (PESERA) model to simulate the spatial distribution of AGB, soil erosion and SOC on a monthly basis. PESERA model simulations indicate an average soil erosion rate across the entire YRB of 7.7 ton/ha/yr, with erosion hotspots concentrated in the Sichuan Basin and the central‐southern regions. The southwestern region and western Sichuan show elevated levels of AGB and SOC, while the eastern plains display lower levels. Erosion rates are lowest in areas designated as artificial land, pasture and grassland, whereas croplands and fruit tree plantations experience the highest erosion rates. In terms of crop types, the highest erosion rates and lowest AGB are observed under fallow and potato cultivation, while the lowest erosion rates and highest AGB are found in rice‐wheat rotation fields. To the best of our knowledge, this is the first study taking detailed crop types and patterns into account while evaluating their effect at a relatively large scale (i.e., YRB). These findings can help to develop sustainable soil management and (cropping) conservation strategies.