Sales dataset

This dataset contains hourly sensor data collected over a period of time. The primary objective is to forecast future sensor values using various time series forecasting methods, such as SARIMA, Prophet, and machine learning models. The dataset includes an ID column, a Datetime column and a Count column, where the Count represents the sensor reading at each timestamp.

This dataset serves as supplementary material to the fully reproducible paper entitled "Comparison of stochastic and machine learning methods for multi-step ahead forecasting of hydrological processes". We provide the R codes and their outcomes. We also provide the reports entitled “Definitions of the stochastic processes’’, “Definitions of the forecast quality metrics’’ and “Selected figures for the qualitative comparison of the forecasting methods’’. The former version of this dataset is available in the provided link.

Abstract

The application of machine learning has become commonplace for problems in modern data science. The democratization of the decision process when choosing a machine learning algorithm has also received considerable attention through the use of meta features and automated machine learning for both classification and regression type problems. However, this is not the case for multistep-ahead time series problems. Time series models generally rely upon the series itself to make future predictions, as opposed to independent features used in regression and classification problems. The structure of a time series is generally described by features such as trend, seasonality, cyclicality, and irregularity. In this research, we demonstrate how time series metrics for these features, in conjunction with an ensemble based regression learner, were used to predict the standardized mean square error of candidate time series prediction models. These experiments used datasets that cover a wide feature space and enable researchers to select the single best performing model or the top N performing models. A robust evaluation was carried out to test the learner's performance on both synthetic and real time series.

Proposed Dataset

The dataset proposed here gives the results for 20 step ahead predictions for eight Machine Learning/Multi-step ahead prediction strategies for 5,842 time series datasets outlined here. It was used as the training data for the Meta Learners in this research. The meta features used are columns C to AE. Columns AH outlines the method/strategy used and columns AI to BB (the error) is the outcome variable for each prediction step. The description of the method/strategies is as follows:

Machine Learning methods:

NN: Neural Network

ARIMA: Autoregressive Integrated Moving Average

SVR: Support Vector Regression

LSTM: Long Short Term Memory

RNN: Recurrent Neural Network

Multistep ahead prediction strategy:

OSAP: One Step ahead strategy

MRFA: Multi Resolution Forecast Aggregation

Time series univariate

Improving the accuracy of prediction on future values based on the past and current observations has been pursued by enhancing the prediction's methods, combining those methods or performing data pre-processing. In this paper, another approach is taken, namely by increasing the number of input in the dataset. This approach would be useful especially for a shorter time series data. By filling the in-between values in the time series, the number of training set can be increased, thus increasing the generalization capability of the predictor. The algorithm used to make prediction is Neural Network as it is widely used in literature for time series tasks. For comparison, Support Vector Regression is also employed. The dataset used in the experiment is the frequency of USPTO's patents and PubMed's scientific publications on the field of health, namely on Apnea, Arrhythmia, and Sleep Stages. Another time series data designated for NN3 Competition in the field of transportation is also used for benchmarking. The experimental result shows that the prediction performance can be significantly increased by filling in-between data in the time series. Furthermore, the use of detrend and deseasonalization which separates the data into trend, seasonal and stationary time series also improve the prediction performance both on original and filled dataset. The optimal number of increase on the dataset in this experiment is about five times of the length of original dataset.

Supplementary material for the paper entitled "One-step ahead forecasting of geophysical processes within a purely statistical framework"Abstract: The simplest way to forecast geophysical processes, an engineering problem with a widely recognised challenging character, is the so called “univariate time series forecasting” that can be implemented using stochastic or machine learning regression models within a purely statistical framework. Regression models are in general fast-implemented, in contrast to the computationally intensive Global Circulation Models, which constitute the most frequently used alternative for precipitation and temperature forecasting. For their simplicity and easy applicability, the former have been proposed as benchmarks for the latter by forecasting scientists. Herein, we assess the one-step ahead forecasting performance of 20 univariate time series forecasting methods, when applied to a large number of geophysical and simulated time series of 91 values. We use two real-world annual datasets, a dataset composed by 112 time series of precipitation and another composed by 185 time series of temperature, as well as their respective standardized datasets, to conduct several real-world experiments. We further conduct large-scale experiments using 12 simulated datasets. These datasets contain 24 000 time series in total, which are simulated using stochastic models from the families of Autoregressive Moving Average and Autoregressive Fractionally Integrated Moving Average. We use the first 50, 60, 70, 80 and 90 data points for model-fitting and model-validation and make predictions corresponding to the 51st, 61st, 71st, 81st and 91st respectively. The total number of forecasts produced herein is 2 177 520, among which 47 520 are obtained using the real-world datasets. The assessment is based on eight error metrics and accuracy statistics. The simulation experiments reveal the most and least accurate methods for long-term forecasting applications, also suggesting that the simple methods may be competitive in specific cases. Regarding the results of the real-world experiments using the original (standardized) time series, the minimum and maximum medians of the absolute errors are found to be 68 mm (0.55) and 189 mm (1.42) respectively for precipitation, and 0.23 °C (0.33) and 1.10 °C (1.46) respectively for temperature. Since there is an absence of relevant information in the literature, the numerical results obtained using the standardised real-world datasets could be used as rough benchmarks for the one-step ahead predictability of annual precipitation and temperature.

TimeSpec4LULC is a smart open-source global dataset of multi-spectral time series for 29 Land Use and Land Cover (LULC) classes ready to train machine learning models. It was built based on the seven spectral bands of the MODIS sensors at 500 m resolution from 2000 to 2021 (262 observations in each time series). Then, was annotated using spatial-temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE).

TimeSpec4LULC contains two datasets: the original dataset distributed over 6,076,531 pixels, and the balanced subset of the original dataset distributed over 29000 pixels.

The original dataset contains 30 folders, namely "Metadata", and 29 folders corresponding to the 29 LULC classes. The folder "Metadata" holds 29 different CSV files describing the metadata of the 29 LULC classes. The remaining 29 folders contain the time series data for the 29 LULC classes. Each folder holds 262 CSV files corresponding to the 262 months. Inside each CSV file, we provide the seven values of the spectral bands as well as the coordinates for all the LULC class-related pixels.

The balanced subset of the original dataset contains the metadata and the time series data for 1000 pixels per class representative of the globe. It holds 29 different JSON files following the names of the 29 LULC classes.

The features of the dataset are:

• ".geo": the geometry and coordinates (longitude and latitude) of the pixel center.

• "ADM0_Code": the GAUL country code.

• "ADM1_Code": the GAUL first-level administrative unit code.

• GHM_Index": the average of the global human modification index.

• "Products_Agreement_Percentage": the agreement percentage over the 15 global LULC products available in GEE.

• "Temporal_Availability_Percentage": the percentage of non-missing values in each band.

• "Pixel_TS": the time series values of the seven spectral bands.

Weather Long-term Time Series Forecasting (2020)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F8734253%2F832430253683be01796f74de8f532b34%2Fweather%20forecasting.png?generation=1730602999355141&alt=media" alt="">

Dataset Description

Weather is recorded every 10 minutes throughout the entire year of 2020, comprising 20 meteorological indicators measured at a Max Planck Institute weather station. The dataset provides comprehensive atmospheric measurements including air temperature, humidity, wind patterns, radiation, and precipitation. With over 52,560 data points per variable (365 days × 24 hours × 6 measurements per hour), this high-frequency sampling offers detailed insights into weather patterns and atmospheric conditions. The measurements include both basic weather parameters and derived quantities such as vapor pressure deficit and potential temperature, making it suitable for both meteorological research and practical applications. You can find some initial analysis using this dataset here: "Weather Long-term Time Series Forecasting Analysis".

File Structure

The dataset is provided in a CSV format with the following columns:

Potential Use Cases

This high-resolution meteorological dataset enables applications across multiple domains. For weather forecasting, the frequent measurements support development of prediction models, while climate researchers can study microclimate variations and seasonal patterns. In agriculture, temperature and vapor pressure deficit data aids crop modeling and irrigation planning. The wind and radiation measurements benefit renewable energy planning, while the comprehensive atmospheric data supports environmental monitoring. The dataset's detailed nature makes it particularly suitable for machine learning applications and educational purposes in meteorology and data science.

Credits

• This data was provided by the Max Planck Institute, and acc...

The market for Time Series Analysis Software is projected to reach $X million by 2033, growing at a CAGR of XX% from 2025 to 2033. Key drivers of this growth include the increasing adoption of IoT devices, the need for real-time data analysis, and the growing complexity of time series data. Additionally, the market is expected to benefit from advancements in artificial intelligence (AI) and machine learning (ML), which can be used to automate time series analysis tasks and improve the accuracy of predictions. The market for Time Series Analysis Software is segmented by application, type, and region. By application, the market is divided into large enterprises and SMEs. By type, the market is divided into cloud-based and on-premises solutions. By region, the market is divided into North America, South America, Europe, the Middle East & Africa, and Asia Pacific. North America is expected to be the largest market for Time Series Analysis Software throughout the forecast period, followed by Europe and Asia Pacific. The growing adoption of IoT devices and the need for real-time data analysis are expected to be the key drivers of growth in these regions.

Time Series Analysis Software Market size was valued at USD 1.8 Billion in 2024 and is projected to reach USD 4.7 Billion by 2032, growing at a CAGR of 10.5% during the forecast period 2026-2032.

Global Time Series Analysis Software Market Drivers

Growing Data Volumes: The exponential growth in data generated across various industries necessitates advanced tools for analyzing time series data. Businesses need to extract actionable insights from large datasets to make informed decisions, driving the demand for time series analysis software.

Increasing Adoption of IoT and Connected Devices: The proliferation of Internet of Things (IoT) devices generates continuous streams of time-stamped data. Analyzing this data in real-time helps businesses optimize operations, predict maintenance needs, and enhance overall efficiency, fueling the demand for time series analysis tools.

Advancements in Machine Learning and AI: Integration of machine learning and artificial intelligence (AI) with time series analysis enhances predictive capabilities and automates the analysis process. These advancements enable more accurate forecasting and anomaly detection, attracting businesses to adopt sophisticated analysis software.

Need for Predictive Analytics: Businesses are increasingly focusing on predictive analytics to anticipate future trends and behaviors. Time series analysis is crucial for forecasting demand, financial performance, stock prices, and other metrics, driving the market growth.

Industry 4.0 and Automation: The push towards Industry 4.0 involves automating industrial processes and integrating smart technologies. Time series analysis software is essential for monitoring and optimizing manufacturing processes, predictive maintenance, and supply chain management in this context.

Financial Sector Growth: The financial industry extensively uses time series analysis for modeling stock prices, risk management, and economic forecasting. The growing complexity of financial markets and the need for real-time data analysis bolster the demand for specialized software.

Healthcare and Biomedical Applications: Time series analysis is increasingly used in healthcare for monitoring patient vitals, managing medical devices, and analyzing epidemiological data. The focus on personalized medicine and remote patient monitoring drives the adoption of these tools.

Climate and Environmental Monitoring: Governments and organizations use time series analysis to monitor climate change, weather patterns, and environmental data. The need for accurate predictions and real-time monitoring in environmental science boosts the market.

Regulatory Compliance and Risk Management: Industries such as finance, healthcare, and energy face stringent regulatory requirements. Time series analysis software helps in compliance by providing detailed monitoring and reporting capabilities, reducing risks associated with regulatory breaches.

Emergence of Big Data and Cloud Computing: The adoption of big data technologies and cloud computing facilitates the storage and analysis of large volumes of time series data. Cloud-based time series analysis software offers scalability, flexibility, and cost-efficiency, making it accessible to a broader range of businesses.

The time series forecasting market, valued at $278.8 million in 2025, is projected to experience robust growth, driven by the increasing adoption of data-driven decision-making across various sectors. The market's Compound Annual Growth Rate (CAGR) of 5.0% from 2019 to 2024 indicates a steady upward trajectory, expected to continue through 2033. Key drivers include the expanding volume and availability of time-series data, coupled with advancements in machine learning and artificial intelligence algorithms that enhance forecasting accuracy and efficiency. Businesses across sectors, including finance, healthcare, and manufacturing, are leveraging these technologies to optimize resource allocation, improve supply chain management, and enhance risk mitigation strategies. The software segment is expected to dominate, given the ease of implementation and scalability of software solutions. However, the service segment is poised for significant growth, driven by increasing demand for specialized expertise in implementing and maintaining these complex systems. Geographical analysis reveals strong market presence in North America, driven by early adoption and technological advancements, but significant growth opportunities exist in Asia-Pacific and Europe as digital transformation initiatives accelerate in these regions. The competitive landscape is marked by a mix of established tech giants like Amazon and Google, alongside specialized time-series analytics vendors such as DataRobot and InfluxData. This competitive dynamic fuels innovation and helps to deliver a range of solutions to meet diverse industry-specific needs. The continuous evolution of time series forecasting techniques, encompassing advanced algorithms and hybrid approaches, is a significant trend shaping the market. Furthermore, the integration of time series forecasting with other analytics tools, such as business intelligence and data visualization platforms, is enhancing its value proposition. Despite the positive outlook, challenges remain, including the need for skilled data scientists to effectively implement and manage these systems, as well as concerns around data security and privacy. Overcoming these challenges will be crucial for sustained market growth. The ongoing development of cloud-based solutions, however, is easing deployment and reducing costs, making time-series forecasting more accessible to a broader range of businesses. This trend, combined with increasing regulatory pressure for data-driven decision making, is further propelling market expansion.

applications of Big Data and Machine Learning are gaining popularity in every industry. Now

Abstract

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable energy resources and electrified transportation, the reliable and secure operation of the electric grid becomes increasingly challenging. In this paper, we present PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML) based approaches towards reliable operation of future electric grids. The dataset is generated through a novel transmission + distribution (T+D) co-simulation designed to capture the increasingly important interactions and uncertainties of the grid dynamics, containing electric load, renewable generation, weather, voltage and current measurements at multiple spatio-temporal scales. Using PSML, we provide state-of-the-art ML baselines on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbance events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement time series. We envision that this dataset will enable advances for ML in dynamic systems, while simultaneously allowing ML researchers to contribute towards carbon-neutral electricity and mobility.

Data Navigation

Please download, unzip and put somewhere for later benchmark results reproduction and data loading and performance evaluation for proposed methods.

wget https://zenodo.org/record/5130612/files/PSML.zip?download=1
7z x 'PSML.zip?download=1' -o./

Minute-level Load and Renewable

• File Name
  • ISO_zone_#.csv: `CAISO_zone_1.csv` contains minute-level load, renewable and weather data from 2018 to 2020 in the zone 1 of CAISO.
• - Field Description
  • Field `time`: Time of minute resolution.
  • Field `load_power`: Normalized load power.
  • Field `wind_power`: Normalized wind turbine power.
  • Field `solar_power`: Normalized solar PV power.
  • Field `DHI`: Direct normal irradiance.
  • Field `DNI`: Diffuse horizontal irradiance.
  • Field `GHI`: Global horizontal irradiance.
  • Field `Dew Point`: Dew point in degree Celsius.
  • Field `Solar Zeinth Angle`: The angle between the sun's rays and the vertical direction in degree.
  • Field `Wind Speed`: Wind speed (m/s).
  • Field `Relative Humidity`: Relative humidity (%).
  • Field `Temperature`: Temperature in degree Celsius.

Minute-level PMU Measurements

• File Name
  • case #: The `case 0` folder contains all data of scenario setting #0.
    • pf_input_#.txt: Selected load, renewable and solar generation for the simulation.
    • pf_result_#.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
• Filed Description
  • Field `time`: Time of minute resolution.
  • Field `Vm_###`: Voltage magnitude (p.u.) at the bus ### in the simulated model.
  • Field `Va_###`: Voltage angle (rad) at the bus ### in the simulated model.
  • Field `P_#_#_#`: `P_3_4_1` means the active power transferring in the #1 branch from the bus 3 to 4.
  • Field `Q_#_#_#`: `Q_5_20_1` means the reactive power transferring in the #1 branch from the bus 5 to 20.

Millisecond-level PMU Measurements

• File Name
  • Forced Oscillation: The folder contains all forced oscillation cases.
    • row_#: The folder contains all data of the disturbance scenario #.
      • dist.csv: Three-phased voltage at nodes in the distribution system via T+D simualtion.
      • info.csv: This file contains the start time, end time, location and type of the disturbance
      • trans.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
  • Natural Oscillation: The folder contains all natural oscillation cases.
    • row_#: The folder contains all data of the disturbance scenario #.
      • dist.csv: Three-phased voltage at nodes in the distribution system via T+D simualtion.
      • info.csv: This file contains the start time, end time, location and type of the disturbance.
      • trans.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
• Filed Description
  • trans.csv
    • - Field `Time(s)`: Time of millisecond resolution.
    • - Field `VOLT ###`: Voltage magnitude (p.u.) at the bus ### in the transmission model.
    • - Field `POWR ### TO ### CKT #`: `POWR 151 TO 152 CKT '1 '` means the active power transferring in the #1 branch from the bus 151 to 152.
    • - Field `VARS ### TO ### CKT #`: `VARS 151 TO 152 CKT '1 '` means the reactive power transferring in the #1 branch from the bus 151 to 152.
  • dist.csv
    • Field `Time(s)`: Time of millisecond resolution.
    • Field `####.###.#`: `3005.633.1` means per-unit voltage magnitude of the phase A at the bus 633 of the distribution grid, the one connecting to the bus 3005 in the transmission system.

Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suffer from limited learnable parameters and small-scale training data. Recently, large language models (LLMs) combining time series with textual prompts have achieved promising performance in MTSF. However, we discovered that current LLM-based solutions fall short in learning disentangled embeddings. We introduce TimeCMA, an intuitive yet effective framework for MTSF via cross-modality alignment. Specifically, we present a dual-modality encoding with two branches: the time series encoding branch extracts disentangled yet weak time series embeddings, and the LLM-empowered encoding branch wraps the same time series with text as prompts to obtain entangled yet robust prompt embeddings. As a result, such a cross-modality alignment retrieves both disentangled and robust time series embeddings, ``the best of two worlds'', from the prompt embeddings based on time series and prompt modality similarities. As another key design, to reduce the computational costs from time series with their length textual prompts, we design an effective prompt to encourage the most essential temporal information to be encapsulated in the last token: only the last token is passed to downstream prediction. We further store the last token embeddings to accelerate inference speed. Extensive experiments on eight real datasets demonstrate that TimeCMA outperforms state-of-the-arts.

Due to fierce problems caused by global warming, more and more countries have implemented various carbon emission restrictions and emissions trading schemes(ETSs) around the world, leading to emergence of global carbon trading markets and a need for accurate carbon price predictions. Our approach enhances Transformer-based time-series models by incorporating news data as strength indicators for price increases. We propose NSEformer, a novel way to combine text data into time-series models using News-Signal Extractor. Through experiments, NSEformer outperforms other methods, offering superior performance in predicting carbon trading prices. Our approach effectively integrates news information, leveraging the expertise of the News-Singal Extractor, and outperforms other fusion strategies.

Time-Series ML Platform Market Outlook

According to our latest research, the global Time-Series ML Platform market size reached USD 2.45 billion in 2024. The market is expected to grow at a robust CAGR of 20.8% between 2025 and 2033, reaching a projected value of USD 16.24 billion by the end of the forecast period. This significant growth is primarily driven by the increasing adoption of machine learning for real-time data analytics, the proliferation of IoT devices generating time-series data, and the rising demand for predictive analytics across diverse industries. As per our latest research, organizations globally are rapidly investing in time-series ML platforms to enhance operational efficiency, drive automation, and gain actionable insights from complex temporal datasets.

One of the primary growth factors for the Time-Series ML Platform market is the exponential rise in the volume of time-stamped data generated across industries. The advent of digital transformation, coupled with the widespread integration of IoT sensors, connected devices, and smart infrastructure, has resulted in a deluge of sequential data that requires advanced analytics solutions. Enterprises are increasingly leveraging time-series machine learning platforms to process, analyze, and extract meaningful patterns from this data, enabling them to make data-driven decisions in real time. The capability of these platforms to support high-frequency data ingestion, automated feature engineering, and scalable model deployment is accelerating their adoption, especially in sectors such as finance, manufacturing, and energy, where operational efficiency and predictive accuracy are critical.

Another significant driver for the market is the growing emphasis on predictive maintenance and anomaly detection applications. Industries such as manufacturing, energy, and utilities are focusing on minimizing downtime and optimizing asset performance by predicting equipment failures and identifying anomalies before they escalate into costly issues. Time-series ML platforms enable organizations to implement advanced predictive maintenance strategies, reducing unplanned outages and maintenance costs. The integration of AI-powered forecasting and anomaly detection models within these platforms further enhances their value proposition, allowing businesses to move from reactive to proactive operational paradigms. This shift is fostering increased investments in time-series ML solutions, as enterprises seek to unlock new levels of productivity and reliability.

Furthermore, the increasing regulatory requirements and the need for robust risk management frameworks are fueling the demand for time-series ML platforms in sectors such as BFSI and healthcare. Financial institutions are utilizing these platforms to detect fraudulent transactions, monitor market volatility, and comply with stringent regulatory guidelines. Similarly, healthcare providers are adopting time-series analytics to track patient vitals, predict disease outbreaks, and optimize resource allocation. The ability of these platforms to deliver real-time insights, ensure data integrity, and support compliance initiatives is making them indispensable tools for risk-sensitive industries. As organizations continue to prioritize data-driven governance and transparency, the adoption of time-series ML platforms is expected to witness sustained growth over the forecast period.

From a regional perspective, North America currently dominates the global Time-Series ML Platform market, accounting for the largest revenue share in 2024. This leadership is attributed to the presence of major technology vendors, high digital maturity, and early adoption of AI and ML technologies across industries. Europe follows closely, driven by robust investments in industrial automation and smart manufacturing initiatives. The Asia Pacific region, however, is poised to witness the fastest growth, propelled by rapid industrialization, expanding digital infrastructure, and increasing investments in AI across emerging economies such as China, India, and Japan. The region's large and diverse population, combined with the proliferation of connected devices, is generating vast amounts of time-series data, creating lucrative opportunities for market players.

Component Analysis

The Component segment of the Time-Series ML Platform market is bifurcated into Software and Services. Software soluti

In the realm of time series prediction modeling, the window size (w) is a critical hyperparameter that determines the number of time units included in each example provided to a learning model. This hyperparameter is crucial because it allows the learning model to recognize both long-term and short-term trends, as well as seasonal patterns, while reducing sensitivity to random noise. This study aims to elucidate the impact of window size on the performance of machine learning algorithms in univariate time series forecasting tasks. To achieve this, we employed 40 time series from two different domains, conducting experiments with varying window sizes using four types of machine learning algorithms: Bagging, Boosting, Stacking, and a Recurrent Neural Network (RNN) architecture. The results reveal that increasing the window size generally enhances the evaluation metric values up to a stabilization point, beyond which further increases do not significantly improve predictive accuracy. This stabilization effect was observed in both domains when w values exceeded 100 time steps. Moreover, the study found that RNN architectures do not consistently outperform ensemble models in various univariate time series forecasting scenarios.

The global time series forecasting market is estimated to reach USD XXX million by 2033, exhibiting a CAGR of XX% during the forecast period. The market is primarily driven by the increasing adoption of artificial intelligence (AI) and machine learning (ML) technologies in various industries, the growing need for predictive analytics to make informed decisions, and the increasing volume of data generated by businesses and organizations. Key trends shaping the market include the rise of cloud-based time series forecasting solutions, the integration of time series forecasting with IoT devices, and the growing adoption of automated time series forecasting tools. The market is dominated by vendors such as Amazon, Google, DataRobot, GMDH Streamline, Seeq Corporation, Time Series Lab, InfluxData, Microsoft, TrendMiner, Anodot, and Trendalyze. North America is expected to remain the largest regional market, followed by Europe and Asia Pacific. The increasing adoption of time series forecasting solutions in industries such as manufacturing, retail, healthcare, and finance is driving the growth of the market in these regions.

Additional file 1. The results of predictive model.