Historical Dataset Research Articles

FROM CALENDAR TIME TO BUSINESS TIME: THE CASE OF COMMODITY MARKETS

We address the problem of modeling commodity forward curves, while preserving empirical features observed in commodity markets. By letting a commodity market to “ live” in the tempo of a business rather than calendar clock, we create a model with a rich but realistic set of features, such as stochastic volatility, stochastic rate of mean reversion and various shapes of forward curves such as backwardation and contango. The model, when applied to extensive historical datasets of crude oil and natural gas forward curves, shows a remarkably good fit to the observed futures prices, also in periods of high volatility and negative prices. The model is developed in such a way that it can be used for a wide variety of applications, ranging from exotic derivatives pricing to risk management of commodity portfolios.

CGAformer: Multi-scale feature Transformer with MLP architecture for short-term photovoltaic power forecasting

Accurately predicting the output power of photovoltaic (PV) systems is an effective means to ensure the reliable and economical operation of grid-connected PV systems. Aiming at the characteristics of PV power generation such as strong volatility, high intermittency and obvious periodicity, a hybrid model named CGAformer based on One-Dimensional Convolutional Neural Networks (CNN1D), Global Additive Attention (GADAttention), and Auto-Correlation is proposed for short-term PV power generation prediction. The model uses CNN1D to extract local features and obtains global weights by improving the GADAttetion obtained by additive attention. Auto-Correlation integrates local features and global weights and identifies repeated patterns in the sequence to obtain highly coupled multi-scale features, and finally generates the final prediction results through Multilayer Perceptron (MLP). In order to verify the effectiveness of the model, this paper uses a historical dataset from a PV system located in Uluru, Australia for sufficient experiments. In the comparative experiments, The overall average RMSE and MAE of CGAformer are improved by 6.82% and 20.46% respectively compared with long short-term memory (LSTM). In addition, ablation experiments and seasonal analysis are used to verify the effectiveness of the model and its excellent generalization ability for different seasons.

NSEMBLE FINE TUNED MULTI LAYER PERCEPTRON FOR PREDICTIVE ANALYSIS OF WEATHER PATTERNS AND RAINFALL FORECASTING FROM SATELLITE DATA

The accurate prediction of weather patterns and rainfall forecasting is critical for various sectors, including agriculture, disaster management, and water resource planning. Traditional models often struggle to capture the complex interactions between atmospheric variables, particularly when integrating diverse types of satellite data (binary, categorical, and numerical). To address this challenge, an ensemble fine-tuned multi-layer perceptron (MLP) model is developed, combining the strengths of multiple machine learning techniques for more robust predictions. The primary problem is the difficulty in handling mixed data types while maintaining high prediction accuracy. Satellite data, including binary indicators (e.g., cloud presence), categorical features (e.g., cloud types), and numerical variables (e.g., temperature, humidity, and wind speed), provide rich information but require specialized processing for effective forecasting. The proposed method involves fine-tuning an ensemble of MLP models with backpropagation, dropout regularization, and batch normalization to reduce overfitting and enhance generalization. The ensemble integrates predictions from individual MLP models, each trained on different subsets of features (binary, categorical, numerical). This technique allows the model to leverage complementary strengths and produce more accurate rainfall forecasts. Satellite data is preprocessed and normalized before training, and categorical variables are one-hot encoded to ensure compatibility with the MLP architecture. Results from testing on historical satellite weather datasets demonstrate significant improvements in forecast accuracy. The ensemble MLP achieved an accuracy of 91.3%, with a precision of 90.7%, recall of 89.5%, and an F1-score of 90.1%. The model performed exceptionally well in identifying critical rainfall events, reducing false positives by 12% compared to traditional models.

A critical reflection on attempts to machine-learn materials synthesis insights from text-mined literature recipes.

Synthesis of predicted materials is the key and final step needed to realize a vision of computationally accelerated materials discovery. Because so many materials have been previously synthesized, one would anticipate that text-mining synthesis recipes from the literature would yield a valuable dataset to train machine-learning models that can predict synthesis recipes for new materials. Between 2016 and 2019, the corresponding author (Wenhao Sun) participated in efforts to text-mine 31 782 solid-state synthesis recipes and 35 675 solution-based synthesis recipes from the literature. Here, we characterize these datasets and show that they do not satisfy the "4 Vs" of data-science-that is: volume, variety, veracity and velocity. For this reason, we believe that machine-learned regression or classification models built from these datasets will have limited utility in guiding the predictive synthesis of novel materials. On the other hand, these large datasets provided an opportunity to identify anomalous synthesis recipes-which in fact did inspire new hypotheses on how materials form, which we later validated by experiment. Our case study here urges a re-evaluation on how to extract the most value from large historical materials-science datasets.

Central Bank Independence and Inflation in Latin America—Through the Lens of History

AbstractWe study the link between central bank independence and inflation by providing narrative and empirical evidence based on Latin America's historical experience. Using a novel historical data set of central bank independence for 17 Latin American countries, we recount the rocky journey traveled by central banks to achieve independence and price stability. Our empirical analysis finds a strong negative association between central bank independence and inflation over the last 80 years, with improvements in independence resulting in a steady decline in inflation. Results are robust to endogeneity concerns and to using alternative central bank independence indices.

Enhancing Long-Term Water Quality Modeling by Addressing Base Demand, demand Patterns, and Temperature Uncertainty Using Unsupervised Machine Learning Techniques.

Water quality modelling in Water Distribution systems (WDS) is frequently affected by uncertainties in input variables such as base demand and decay constants. When utilizing simulation tools like EPANET, which necessitate exact numerical inputs, these uncertainties can result in inaccurate simulations. This study proposes a novel framework that leverages unsupervised machine learning, specifically a Gaussian Mixture Model (GMMs), to represent and integrate these uncertainties in the simulation. By classifying historical water demand into fuzzy clusters, the framework allows for certain linguistic inputs (e.g., "high" or "low" demand) to be used in water quality simulations. The framework also incorporates representative hourly demand patterns and temperature-dependent chlorine decay constants based on historical data correlations. Validations were conducted on the Anytown network using WNTR-EPANET, comparing simulated chlorine residuals with Validation data from 181 steady-state simulations. The simulation through the framework achieved a Jensen-Shannon Divergence (JSD) of less than 0.008 across all demand clusters, indicating high similarity between predicted and actual probability distributions . In comparison to other simulation scenarios tested, which exhibited increased variability (JSD > 0.18), the proposed framework demonstrated improved accuracy in representing chlorine residual distributions. The methodology is adaptable to other systems, if similar historical datasets containing key variables, such as flow rates and temperature, are provided. While the framework offers a more flexible and accurate approach to handling uncertainties in WDS, its effectiveness is contingent upon the availability of robust historical demand and temperature data for decay constant calibration.

Leveraging AI and ML for Next-Generation Cloud Security: Innovations in Risk-Based Access Management

In the increasing reliance on the cloud computing era, securing digital assets against sophisticated cyber threats has become a critical concern for organizations globally. Traditional security mechanisms, which often rely on static and pre-defined access control policies, must be revised to address these threats' dynamic and evolving nature. This study investigates the application of Artificial Intelligence (AI) and Machine Learning (ML) in enhancing cloud security through the development of advanced Risk-Based Access Management (RBAM) systems. The primary objective is to evaluate how AI and ML can improve dynamic access control, threat prediction, and mitigation strategies within cloud environments. The research adopts a mixed-methods approach, combining quantitative analysis of RBAM system performance with qualitative insights from cybersecurity experts. AI/ML models were developed using extensive historical access log datasets and integrated into a cloud-based RBAM prototype. The system's performance was assessed based on its accuracy in threat detection, reduction in false positives, and effectiveness in dynamically adjusting access controls. Results indicate that the AI-enhanced RBAM system significantly outperforms traditional methods, achieving a 30% reduction in false positives and a 25% decrease in unauthorized access incidents. Additionally, AI-driven threat prediction models demonstrated high accuracy, enabling preemptive actions to mitigate potential security breaches. These findings highlight the transformative potential of AI and ML in cloud security, providing a more adaptive and proactive defense against emerging threats. The study concludes with recommendations for refining AI/ML models and exploring their application in other areas of cloud security, emphasizing the need for continued innovation to safeguard the increasingly complex digital landscapes that organizations operate within today.

Enhancing hydrological predictions: optimised decision tree modelling for improved monthly inflow forecasting

ABSTRACT The utilisation of modelling tools in hydrology has been effective in predicting future floods by analysing historical rainfall and inflow data, due to the association between climate change and flood frequency. This study utilised a historical dataset of monthly inflow and rainfall for the Terengganu River in Malaysia, and it is renowned for its hydrological patterns that exhibit a high level of unpredictability. The evaluation of the predictive precision and effectiveness of the Optimised Decision Tree ODT model, along with the RF and GBT models, in this study involved analysing several indicators. These indicators included the correlation coefficient, mean absolute error, percentage of relative error, root mean square error, Nash-Sutcliffe efficiency, and accuracy rate. The research results indicated that the ODT and RF models performed better than the GBT model in predicting monthly inflows. The ODT model, as well as the RF and GBT models, showed validation results with average accuracies of 94%, 91%, and 92%, respectively. The R² values were 90.2%, 84.8%, and 96.0%, respectively, and the NES values ranged from 0.92 to 0.94. The results of this research have greater implications, extending beyond the forecasting of monthly inflow rates to encompass other hydro-meteorological variables that depend exclusively on historical input data.

Harvester selection and observed mercury levels in Eastern Beaufort Sea and Western Hudson Bay beluga whales (Delphinapterus leucas)

Mercury in marine biota has been extensively studied across Inuit Nunaat because it bioaccumulates and biomagnifies in high trophic level species, such as the beluga whale (Delphinapterus leucas), or qilalugaq in Inuktut. Qilalugaait (pl) are a staple in many coastal Inuit communities, including Tuktoyaktuk, Northwest Territories and Arviat, Nunavut. We examine how total mercury (THg) concentrations in two beluga populations are influenced by biased sampling resulting from local harvester preferences. We examined historical THg in skin, muscle, and liver (1980's to 2022) together with local qualitative interviews from two beluga-harvesting communities. Age and length bins were used to compare similar sized and aged whales between locations, where males (350 - 400 cm, and 20–30 years) and females (330–400 cm, and 15–30 years) were segregated. The interviews revealed distinct preferences whereby harvesters in Tuktoyaktuk actively sought larger (length) male whales, whereas harvesters in Arviat, selected wide and even range across size and sex. These local preferences were also evident in the historical dataset, with the median age and lengths were 31 years and 389.0 cm in Tuktoyaktuk (n = 461) and 23 and 336.0 cm in Arviat (n = 146). For males, mean and median THg concentrations were higher in beluga harvested from Tuktoyaktuk than Arviat in all three tissues with age and lengths combined, yet in the selected age and length bins, there was no difference in mean and median THg in the muscle tissue, and in median liver THg. There were significant differences in mean and median skin THg and in mean liver THg concentrations between males. In female whales, THg concentrations did not differ between Tuktoyaktuk and Arviat (in ages and lengths combined and in selected age bins across all tissues), excluding median muscle THg concentration. This study indicated that differences in THg concentrations that were previously observed resulted from hunter preferences in these two communities.

Forecasting of meteorological drought using ensemble and machine learning models

This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.

Optimizing Agricultural Data Analysis Techniques through AI-Powered Decision-Making Processes

The agricultural sector is undergoing a transformative paradigm shift with the integration of advanced technologies, particularly artificial intelligence (AI), to enhance data analysis techniques and streamline decision-making processes. This paper delves into the integration of advanced technologies in agriculture, focusing specifically on optimizing data analysis through artificial intelligence (AI) to strengthen decision-making processes in farming. We present a novel AI-powered model that leverages historical agricultural datasets, utilizing a comprehensive array of established machine learning algorithms to enhance the prediction and classification of agricultural data. This work provides tailored algorithm recommendations, bypassing the need to deploy and fine-tune numerous algorithms. We approximate the accuracy of suitable algorithms, highlighting those with the highest precision, thus saving time by leveraging pre-trained AI models on historical agricultural data. Our method involves three phases: collecting diverse agricultural datasets, applying multiple classifiers, and documenting their accuracy. This information is stored in a CSV file, which is then used by AI classifiers to predict the accuracy of new, unseen datasets. By evaluating feature information and various data segmentations, we recommend the configuration that achieves the highest accuracy. This approach eliminates the need for exhaustive algorithm reruns, relying on pre-trained models to estimate outcomes based on dataset characteristics. Our experimentation spans various configurations, including different training–testing splits and feature sets across multiple dataset sizes, meticulously evaluated through key performance metrics such as accuracy, precision, recall, and F-measure. The experimental results underscore the efficiency of our model, with significant improvements in predictive accuracy and resource utilization, demonstrated through comparative performance analysis against traditional methods. This paper highlights the superiority of the proposed model in its ability to systematically determine the most effective algorithm for specific agricultural data types, thus optimizing computational resources and improving the scalability of smart farming solutions. The results reveal that the proposed system can accurately predict a near-optimal machine learning algorithm and data structure for crop data with an accuracy of 89.38%, 87.61%, and 84.27% for decision tree, random forest, and random tree algorithms, respectively.

Enhancing Agricultural Productivity: A Machine Learning Approach to Crop Recommendations

AbstractAgriculture constitutes the foundational pillar of the global economy, engaging a substantial segment of the workforce and making a considerable contribution to the Gross Domestic Product (GDP). However, agricultural productivity faces numerous challenges, including varying climatic conditions, soil types, and limited access to modern farming practices. Developing intelligent agricultural systems becomes imperative to address these challenges and enhance agricultural productivity. Therefore, this paper aims to present a Machine Learning (ML) based crop recommendation system tailored for the farming landscape. The proposed system utilizes historical data on climatic conditions, soil properties, crop yields, and farmer preferences to provide personalized crop recommendations. The goal of this study is to appraise the efficacy of nine distinct ML models—Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Bagging (BG), AdaBoost (AB), Gradient Boosting (GB), and Extra Trees (ET) to generate practical recommendations for crop selection. Numerous preprocessing methods are employed to cleanse and normalize the data, thereby ensuring its appropriateness for model training. The ML models are trained using historical data sets, including temperature, rainfall, humidity, soil pH, and nutrient levels, where crop yields are correlated with environmental and agronomic factors. The models undergo fine-tuning through methods such as cross-validation to enhance their performance and ensure robustness. Among those models, Radom Forest has achieved the highest accuracy (99.31%). The proposed Machine Learning-based crop recommendation system offers a promising approach to addressing the challenges faced by the farmers. By leveraging advanced data analytics and artificial intelligence techniques, the system empowers farmers with timely and personalized recommendations, ultimately leading to improved agricultural productivity, food security, and economic prosperity.

Shapley visual transformers for image-to-text generation

In the contemporary landscape of the web, text-to-image generation stands out as a crucial information service. Recently, deep learning has emerged as the cutting-edge methodology for advancing text-to-image generation systems. However, these models are typically constructed using domain knowledge specific to the application at hand and a very particular data distribution. Consequently, data scientists must be well-versed in the relevant subject. In this research work, we target a new foundation for text-to-image generation systems by introducing a consensus method that facilitates self-adaptation and flexibility to handle different learning tasks and diverse data distributions. This paper presents I2T-SP (Image-to-Text Generation for Shapley Pruning) as a consensus method for general-purpose intelligence without the assistance of a domain expert. The trained model is developed using a general deep-learning approach that investigates the contribution of each model in the training process. Multiple deep learning models are trained for each set of historical data, and the Shapley Value is determined to compute the contribution of each subset of models in the training. Subsequently, the models are pruned according to their contribution to the learning process. We present the evaluation of the generality of I2T-SP using different datasets with varying shapes and complexities. The results reveal the effectiveness of I2T-SP compared to baseline image-to-text generation solutions. This research marks a significant step towards establishing a more adaptable and broadly applicable foundation for image-to-text generation systems.

HexaLCSeg: A historical benchmark dataset from Hexagon satellite images for land cover segmentation [Software and Data Sets

HexaLCSeg: A historical benchmark dataset from Hexagon satellite images for land cover segmentation [Software and Data Sets

Subtle changes in plant diversity in the Bavarian Alps over the past eight decades.

Historical resurveys represent a unique opportunity to analyze vegetation dynamics over longer timescales than is typically achievable. Leveraging the oldest historical dataset of vegetation change in the Bavarian Alps, Germany, we address how environmental conditions, vegetation composition, and functional diversity in the calcareous grasslands of the Schachen region have changed across different elevational ranges over an 83-year timeframe. We document changes in regional average temperature and precipitation. We use indicator values (IV) for species' ecological preferences and their palatability to grazers to infer local conditions (temperature, soil moisture/fertility, and grazing regime). We further estimate changes in temporal beta-diversity and functional trait community composition between historical (1936) and contemporary (2019) surveys in two elevational (subalpine and alpine) belts. Both subalpine and alpine sites became drier; subalpine sites also became warmer with more palatable plants. Species occurrence and abundance in the Schachen region has not changed substantially over time despite changing macroclimate and local environmental conditions under anthropogenic change. Yet these grasslands have experienced several "invisible" changes in functional composition over the past 80 years. As the Schachen has become drier, species with traits related to drought tolerance and animal-based dispersal have increased in dominance. Specifically, in alpine sites, community-weighted means revealed that with low fecundity, higher potential for endo- and epizoochory (seed dispersal via animal gut and fur, respectively), higher foliar frost tolerance, and deeper dormancy increased in dominance. Similar trends were found for increasing dominance of low fecundity, epizoochorous species in subalpine sites. Vegetation data from resurveying historical plots in combination with changes in local conditions, classic biodiversity indices, and functional trait indices can provide more holistic insights into changes in the environment and potential impacts of those environmental changes on long-term plant community and functional diversity.

Metafeature Selection via Multivariate Sparse-Group Lasso Learning for Automatic Hyperparameter Configuration Recommendation.

The performance of classification algorithms is mainly governed by the hyperparameter settings deployed in applications, and the search for desirable hyperparameter configurations usually is quite challenging due to the complexity of datasets. Metafeatures are a group of measures that characterize the underlying dataset from various aspects, and the corresponding recommendation algorithm fully relies on the appropriate selection of metafeatures. Metalearning (MtL), aiming to improve the learning algorithm itself, requires development in integrating features, models, and algorithm learning to accomplish its goal. In this article, we develop a multivariate sparse-group Lasso (SGLasso) model embedded with MtL capacity in recommending suitable configurations via learning. The main idea is to select the principal metafeatures by removing those redundant or irregular ones, promoting both efficiency and performance in the hyperparameter configuration recommendation. To be specific, we first extract the metafeatures and classification performance of a set of configurations from the collection of historical datasets, and then, a metaregression task is established through SGLasso to capture the main characteristics of the underlying relationship between metafeatures and historical performance. For a new dataset, the classification performance of configurations can be estimated through the selected metafeatures so that the configuration with the highest predictive performance in terms of the new dataset can be generated. Furthermore, a general MtL architecture combined with our model is developed. Extensive experiments are conducted on 136 UCI datasets, demonstrating the effectiveness of the proposed approach. The empirical results on the well-known SVM show that our model can effectively recommend suitable configurations and outperform the existing MtL-based methods and the well-known search-based algorithms, such as random search, Bayesian optimization, and Hyperband.

Generative AI in Fintech: Advancing Risk Assessment and Fraud Detection in Digital Payment Technologies

This article explores the transformative potential of artificial intelligence (AI), particularly generative AI, in enhancing risk assessment and fraud detection within digital payment technologies. As financial fraud evolves in sophistication, traditional detection methods often fall short. We propose a novel approach leveraging generative AI to create synthetic data that mimics real-world scenarios, thereby training more comprehensive and adaptive fraud detection models. This article addresses limitations in historical datasets, improves the accuracy of predictive models, and reduces false positives. Furthermore, we demonstrate how this approach enables proactive detection of emerging fraud trends, allowing fintech firms to stay ahead in the ongoing arms race against fraudsters. Our findings suggest that integrating generative AI into fraud detection systems can significantly enhance the security and reliability of digital payment platforms, potentially revolutionizing risk management in the fintech industry. This article contributes to the growing body of knowledge on AI applications in financial security and provides a foundation for future developments in this critical area.

Eliciting the Discount Parameter in a Power Prior Method on the Basis of the Type I Error Consideration

In Bayesian clinical trial design, the power prior methodology offers a flexible framework for incorporating historical data into the analysis. One critical aspect of this approach is determining the effective sample size, which quantifies the amount of information borrowed from the historical dataset. In this article, we derive a formula for computing the effective sample size of a power prior by eliciting the discount parameter on the basis of the Type I error consideration. Our formula takes into account various factors, including the sample size of the historical dataset and the maximally allowable Type I error rate. We demonstrate the utility of our formula through illustrative examples and provide practical guidelines for its application in clinical trial planning, using a pediatric schizophrenia trial as an example. By accurately estimating the effective sample size, researchers can enhance the efficiency and validity of Bayesian analyses in the context of historical data borrowing. Supplementary materials for this article are available online.

A global database of tsunami deposits

AbstractGeomorphic environments play a crucial role in influencing the preservation and characteristics of tsunami deposits. This paper introduces a global database of tsunami deposits, encompassing information on deposit locations, thematic data such as geomorphic environments and proxies and bibliographic details. Additionally, the database features maps incorporating environmental parameters and the precise locations of tsunami deposits. The primary utility of this database lies in assessing progress and identifying gaps in knowledge. It also involves analysing the relationship between environmental parameters and interpreting areas with varying probabilities of tsunami deposit preservation. The files are readily compatible with GIS software and can seamlessly integrate into spatial databases associated with tsunamis or other hazards. This contributes significantly to disaster risk management, enhancing preparedness and response efforts by providing a comprehensive historical dataset on tsunamis. Future applications of the database include the incorporation of modern deposits, boulders and new data from paleotsunami and historical studies. By enhancing data with thematic information, such as dating techniques and creating timelines, the database facilitates a more comprehensive understanding. The correlation between geomorphic environments and proxies aids in selecting sampling sites and identifying suitable proxies for analysis. Encouraging an open‐access approach, this database invites all interested researchers to include and modify additional information. The information compiled for this database serves multiple purposes: (1) assessing the global distribution of tsunami deposits; (2) identifying knowledge gaps in tsunami deposits; (3) guiding the selection of study areas for further research and finally; (4) enabling a meta‐analysis of the information gathered.

Development of a leaf area index-based relative threshold method for identifying agricultural drought areas

Considering the global aggravated agricultural drought condition, the availability of reliable historical agricultural drought information with high spatiotemporal resolution is crucial for accurate drought monitoring, effective water resources management, and sustainable agricultural development. However, the coarse spatiotemporal resolution of available historical agricultural drought datasets imposes great limitations on drought prevention and mitigation. Recognizing the research gap, this study developed a novel approach of leaf area index (LAI) relative thresholds to generate a 500 m-resolution agricultural drought areas dataset in the North China Plain (NCP) spanning the timeframe from 2006 to 2019. A range of key LAI relative thresholds were established to capture various levels of agricultural drought severity. Subsequently, a 500 m-resolution agricultural drought area dataset was generated, encompassing critical parameters of drought-covered area, drought-damaged area, and crop failure area for both summer-harvest and autumn-harvest seasons in each year. The relative thresholds for drought-covered area, drought-damaged area, and crop failure area yielded percentages of 56 %, 51 %, 34 % for summer-harvest crops and 45 %, 41 %, 28 % for autumn-harvest crops, respectively. To validate the credibility of the generated approach, historical agricultural drought areas data from the Bulletin of Flood and Drought Disasters in China were juxtaposed across various harvest seasons and multiple years. The spatial verification in the Hebei Province (one main province of the NCP) revealed a remarkable consistency between the newly generated dataset and the authentic dataset, demonstrating correlation efficiency estimates ranging from 0.70 to 0.83. The developed approach gives insights into the spatial distribution and coherence of agricultural drought impacted areas and sheds light on revealing the inter-annual dynamics of crop growing seasons. It can support for impact-based agricultural drought monitoring and prediction, and subsequently assist in optimizing agricultural water management and ensuring global food security.