Skip to main content
CARLA HQ
DATASET PROFILE / TIME SERIES

Global Sovereign Carbon Dioxide (CO2) Emissions

Covers annual sovereign carbon dioxide (CO2) emissions across 191 nations spanning 60 historical years at yearly cadence. Evaluates a 5-year forecast horizon to project sovereign decarbonization trajectories and national emissions reduction targets.

Environmental Science & Macroeconomics Public Services & Risk use casesNACE M72Time Series ForecastingYearly Cadence5 Steps HorizonMarkdown ↗Target: targetfev / AutoGluon ↗
✨ Try in CarlaInstall Chrome Extension ↗100% In-Browser WebGPU • Zero Cloud Upload
11,460Records (Rows)
191Series Sequences
YearlySampling Cadence
5 YearsForecast Horizon (9 Windows)
1 Year (Annual)
Dominant Seasonality?No intra-year seasonality (annual cadence; seasonality parameter = 1); exhibits long-wave macroeconomic business cycles and structural multi-decade industrial policy shifts.
41 Methodsfev Leaderboard (SQL)
BUSINESS CONTEXT & OBJECTIVEClimate Policy & Decarbonization (M72)

Business Objective: Global Sovereign Carbon Dioxide (CO2) Emissions

01Business Context

National environmental agencies, international treaty bodies (UNFCCC), sovereign wealth funds, and ESG risk committees require multi-year emissions projections to calibrate climate transition risk, verify Nationally Determined Contributions (NDCs), and assess global carbon budgets on an annual cycle.

02Analytical Objective

Forecast territorial carbon dioxide emissions for 191 sovereign states over a 5-year forward horizon (H=5) using six decades of annual historical emission dynamics.

03Economic & Decision Impact

Under-forecasting emissions obscures structural transition bottlenecks, leaving governments exposed to treaty penalties, underfunded carbon capture infrastructure, and unmitigated climate liability. Over-forecasting misallocates capital toward stranded decarbonization assets and penalizes sovereign credit ratings through over-stringent regulatory burdens.

04Temporal Dynamics & Covariate Information Flow

Dominant Seasonality: No intra-year seasonality (annual cadence; seasonality parameter = 1); exhibits long-wave macroeconomic business cycles and structural multi-decade industrial policy shifts.

Covariates & Information Flow: Historically driven by sovereign GDP growth, demographic expansion, primary energy mix (coal, gas, renewables), heavy industry output, and policy inflection milestones such as the Kyoto Protocol and Paris Agreement.

ML Benchmark Narrative

Due to smooth non-seasonal annual trends across 60 time steps, classical statistical baselines like AutoARIMA and damped Holt-Winters ETS deliver stable linear drift extrapolations but struggle with structural economic decoupling. Gradient boosted trees (LightGBM lag models) capture non-linear sovereign economic shifts when cross-country features are shared, while zero-shot time series foundation models (such as Mistral's Timestral and MOIRAI) excel at generalizing multi-country macroeconomic transition curves without overfitting short series lengths.

Source Origin:Global Carbon Project / World Bank
Creator:Friedlingstein et al., Global Carbon Budget (2023)
License:CC-BY-4.0
IN-BROWSER FORECAST DEMO

Forecast this dataset in your browser

A representative series is read directly from this dataset’s Parquet file. Move the forecast start, compare held-out observations, and toggle available numeric covariates with Timestral 5M (12 MB) or switch to ci-proto (~346 MB, WebGPU). Benchmark scores above use the stated evaluation setup.

Live sample from dataset Parquet
Timestral 5M · WebGPU
Nord Pool Day-Ahead Electricity PricesHourly · €/MWh
Forecast History
Loading sample data…
Covariates
FEATURE SPECIFICATION & DATA DICTIONARY

Target & Feature Column Definitions

Exhaustive business definitions, measurement units, roles, and target variables across all 3 columns.

INFORMATION AVAILABILITY & TEMPORAL PROTOCOL

Known Future Covariates vs. Historically Observed Covariates

Multi-step forecasting models must respect the arrow of time and real-world information availability. FEV benchmarks and Carla strictly distinguish between features known across the forward prediction window versus realizations available only up to the forecast origin.

FUTURE KNOWN COVARIATESLegitimately available at test time (steps t+1 to t+H)

Scheduled promotions (such as Rossmann's Promo), calendar events (school/state holidays), and operational forecasts (such as Nord Pool's day-ahead grid load and wind power forecasts). These are deterministic or published before market clearing, allowing foundation models to legitimately condition on them across future steps.

HISTORICALLY OBSERVED COVARIATESStrictly restricted to history (time ≤ t)

Stochastic operational observations (such as Rossmann's actual customer footfall Customers, Rohlik's actual precipitation and snowfall, or sudden warehouse shutdowns). Because these are only realized in real-time, future values must never enter a prediction to prevent lookahead target leakage.

Observed Dataset Dynamics: Historically driven by sovereign GDP growth, demographic expansion, primary energy mix (coal, gas, renewables), heavy industry output, and policy inflection milestones such as the Kyoto Protocol and Paris Agreement.
ColVariable / Feature NameRoleTypeUnit / ScaleDescription & Business Meaning
CtargetAnnual Territorial CO2 EmissionsTARGETNUMkt CO2
Total annual territorial carbon dioxide emissions produced from fossil fuel combustion and industrial processes.
AidCountry / Sovereign EntitySERIES IDCAT—
Unique sovereign state, country, or territorial identifier for each time series.
BtimestampReporting YearTIMETIMEyear
Annual reporting timestamp marking the end of each calendar observation period from 1960 onwards.
DATASET PREVIEW

Interactive Data Table

Explore rows, feature values, and target labels for Global Sovereign Carbon Dioxide (CO2) Emissions.

Loading dataset...
GLOBAL BENCHMARK PROVENANCE (FEV-BENCH)

Foundation Models vs Traditional ML & Baselines (35 Methods)

Empirical evaluation directly from the AutoGluon fev benchmark suite. Global aggregate ranking: The win rates and skill scores below represent cross-dataset performance across all 100 standardized tasks in fev-bench, rather than results isolated to Global Sovereign Carbon Dioxide (CO2) Emissions.

Benchmark Provenance & Latency Measurement:
100-Task Global Aggregation:The rankings evaluate zero-shot foundation models across 100 heterogeneous benchmark tasks in fev-bench, measuring aggregate generalization across diverse frequencies and prediction horizons.
FEV Python vs. In-Browser WebGPU Timing:The "FEV Latency" column reports server-side Python execution times from the official AutoGluon FEV benchmark. Independently, Carla measures and reports true client-side WebGPU execution inside Google Sheets (207ms on this dataset) with zero server reliance.
#1 Official Ranked Model?ci-proto from Continuous Intelligence ranks #1 on the 35-method official fev-bench view (90.0% SQL win rate; #3 overall at 84.37% across all 52 evaluated models) and can also run locally in our browser WebGPU demo.
ci-proto90.0% Win Rate • 0.53s FEV latency
Evaluated Methods?35 official leaderboard methods (52 total evaluated including closed APIs and checkpoint variants across foundation models, deep neural architectures, trees, and statistical baselines).
35 Official52 total • Continuous Intelligence, H2O.ai, Mistral AI, Google, AWS
Primary Evaluation Metric?Scaled Quantile Loss (SQL) penalizes both point prediction errors and quantile miscalibration across 9 probabilistic levels (p10 to p90).
SQL & MASEProbabilistic calibration
Independent Browser WebGPU?Carla Engine executes Timestral-123M locally in Google Sheets via WebGPU shaders, while ci-proto can also be tested directly in-browser via ONNX Runtime WebGPU and Rust/WASM above.
207ms / windowTimestral-123M (Carla Engine) • Zero server upload
RankMethod / ModelFamilyOrganization
SQL Win Rate?Average win rate (%) against all competing models across the benchmark tasks under Scaled Quantile Loss.
SQL Skill?Normalized skill score relative to the Seasonal Naive baseline (0% = baseline, higher is better).
MASE Win Rate?Average win rate (%) under Mean Absolute Scaled Error.
FEV Latency?FEV benchmark reference latency measured in server Python (median seconds per 100 series). Independent in-browser WebGPU execution for Carla is reported in the telemetry card above.
Link
#1ci-protoFoundation ModelContinuous Intelligence90.0%+51.5%88.4%0.53sRepo ↗
#2TimeH2O-v1Foundation ModelH2O.ai89.7%+50.8%88.2%2.82sRepo ↗
#3Timestral-209MFoundation ModelMistral AI87.1%+50.4%85.4%0.51sRepo ↗
#4t0-gammaFoundation ModelThe Forecasting Company84.7%+49.4%82.0%4.38sRepo ↗
#5Simons-297MFoundation ModelAbel AI Lab82.0%+48.4%80.9%0.94sRepo ↗
#6timesfm-3Foundation ModelGoogle79.3%+49.0%77.6%3.41sRepo ↗
#7iAmTime-base-forecastFoundation ModelWalmart Labs73.7%+46.8%72.5%0.56sRepo ↗
#8Chronos-2Foundation ModelAWS72.2%+47.3%69.9%0.84sRepo ↗
#9t0-betaFoundation ModelThe Forecasting Company69.9%+46.6%66.9%2.29sRepo ↗
#10Toto-2.0-2.5BBaselineCommunity69.4%+44.4%67.8%5.58sRepo ↗
#11TiRex-2Foundation ModelNX-AI69.2%+45.5%66.3%0.27sRepo ↗
#12TiRexFoundation ModelNX-AI62.2%+42.6%58.0%0.24sRepo ↗
#13Toto-2.0-22mBaselineCommunity61.6%+42.9%59.4%0.25sRepo ↗
#14TimesFM-2.5BaselineCommunity58.4%+42.2%56.7%1.87sRepo ↗
#15TabPFN-TS-3Foundation ModelPrior Labs55.5%+43.1%53.3%235sRepo ↗
#16TS-ICLFoundation ModelEDF-Lab55.1%+43.1%53.4%2.49sRepo ↗
#17citras-fmFoundation ModelHitachi52.9%+41.2%50.6%0.60sRepo ↗
#18FlowStateFoundation ModelIBM52.7%+39.9%53.0%2.29sRepo ↗
#19Toto-1.0BaselineCommunity51.6%+40.8%48.8%22.35sRepo ↗
#20TabPFN-TSFoundation ModelPrior Labs50.5%+41.5%48.0%109sRepo ↗
#21Moirai-2.0BaselineCommunity46.2%+39.3%44.2%0.35sRepo ↗
#22Chronos-BoltFoundation ModelAWS45.4%+38.9%42.9%0.26sRepo ↗
#23TFTDeep Learning—34.7%+32.2%31.6%829sRepo ↗
#24Sundial-BaseFoundation ModelTsinghua University30.8%+33.4%37.0%8.01sRepo ↗
#25Stat. EnsembleBaselineCommunity30.6%+20.7%33.6%147sRepo ↗
#26PatchTSTDeep Learning—30.0%+30.1%27.8%664sRepo ↗
#27DeepARDeep Learning—28.9%+29.1%25.9%1113sRepo ↗
#28AutoARIMAStatistical Baseline—26.6%+21.3%24.2%20.14sRepo ↗
#29AutoETSStatistical Baseline—22.5%-26.8%24.1%3.48sRepo ↗
#30CatBoostTree Ensemble—21.8%+23.0%37.5%29.48sRepo ↗
#31LightGBMTree Ensemble—20.3%+21.0%35.7%3.03sRepo ↗
#32AutoThetaStatistical Baseline—17.9%+5.5%22.2%3.28sRepo ↗
#33Seasonal NaiveBaselineCommunity12.0%0.0%13.2%0.48sRepo ↗
#34NaiveStatistical Baseline—7.8%-45.4%12.2%0.47sRepo ↗
#35DriftStatistical Baseline—7.0%-45.8%11.1%0.45sRepo ↗
STATISTICAL DISTRIBUTIONS

Variable Schema & Summary Distributions

Observed numerical ranges, category cardinalities, missing rates, and sample values across 11,460 rows.

ColVariable NameTypeMissingDistinctSummary Stats / DistributionSample Values
CtargetTARGETNUM08,292[-80.67400360107422, 34344008] μ=992162 σ=3049003414.3710021972656491.37799072265625689.39599609375
AidCAT0191—AfghanistanAfghanistanAfghanistan
BtimestampCAT060—1960-12-31T00:00:001961-12-31T00:00:001962-12-31T00:00:00
FREQUENTLY ASKED QUESTIONS

Frequently Asked Questions: Global Sovereign Carbon Dioxide (CO2) Emissions

Common questions regarding the Global Sovereign Carbon Dioxide (CO2) Emissions dataset, machine learning task formulations, and in-browser tabular inference.

What is the forecasting horizon for Global Sovereign Carbon Dioxide (CO2) Emissions?

The standardized forecasting horizon is 5 years (H=5) at an annual cadence, matching international multi-year climate policy review cycles and sovereign NDC updates.

Can I run zero-server forecasts on this dataset in Google Sheets?

Yes, Carla enables zero-server in-context time series forecasting directly in spreadsheets using modern foundation models such as Mistral's Timestral, requiring no remote API round-trips or server infrastructure.

Which models perform best on Global Sovereign Carbon Dioxide (CO2) Emissions?

Zero-shot foundation models like Mistral's Timestral and MOIRAI excel on multi-entity yearly series by leveraging cross-country macro trends, while tuned LightGBM and AutoARIMA baselines provide strong competitive performance on smooth, monotonic trajectories.

LIVE EVALUATION IN GOOGLE SHEETS

Forecast with Carla: Global Sovereign Carbon Dioxide (CO2) Emissions

Open the pre-loaded Google Sheet and let Carla generate multi-step probabilistic forecasts using Mistral's Timestral directly inside your browser with zero server uploads.

Step 1

Launch Carla

Click once to open the spreadsheet and Carla side panel together.

Step 2

Review the Setup

Carla auto-detects the target sequence, frequency cadence, and temporal covariates.

Step 3

Forecast & Calibrate

Generate multi-step quantile forecasts with zero server uploads.

Provenance & Attribution

Friedlingstein et al., Global Carbon Budget 2023, Earth System Science Data, 15, 5301–5369, 2023.

License: Open AccessData Source: autogluon/fev_datasetsOriginal Source: https://globalcarbonbudget.org/