The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index; 4 of the 8 sources its claims cite were checked for support.
Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature
Open accessPublished version of a preprint
Abstract
Abstract. Both the root mean square error (RMSE) and the mean absolute error (MAE) are regularly employed in model evaluation studies. Willmott and Matsuura (2005) have suggested that the RMSE is not a good indicator of average model performance and might be a misleading indicator of average error, and thus the MAE would be a better metric for that purpose. While some concerns over using RMSE raised by Willmott and Matsuura (2005) and Willmott et al. (2009) are valid, the proposed avoidance of RMSE in favor of MAE is not the solution. Citing the aforementioned papers, many researchers chose MAE over RMSE to present their model evaluation statistics when presenting or adding the RMSE measures could be more beneficial. In this technical note, we demonstrate that the RMSE is not ambiguous in its meaning, contrary to what was claimed by Willmott et al. (2009). The RMSE is more appropriate to represent model performance than the MAE when the error distribution is expected to be Gaussian. In addition, we show that the RMSE satisfies the triangle inequality requirement for a distance metric, whereas Willmott et al. (2009) indicated that the sums-of-squares-based statistics do not satisfy this rule. In the end, we discussed some circumstances where using the RMSE will be more beneficial. However, we do not contend that the RMSE is superior over the MAE. Instead, a combination of metrics, including but certainly not limited to RMSEs and MAEs, are often required to assess model performance.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This technical note argues against the recommendation by Willmott and Matsuura (2005) and Willmott et al. (2009) to abandon RMSE in favor of MAE, showing that RMSE is not ambiguous in meaning and is more appropriate when errors are expected to be Gaussian. The authors also demonstrate that RMSE satisfies the triangle inequality required of a distance metric, contrary to the earlier claims, while concluding that a combination of metrics is often needed.
Key findings
- RMSE is not ambiguous in its meaning, contrary to Willmott et al. (2009); it is more appropriate than MAE when the error distribution is expected to be Gaussian, whereas MAE suits uniformly distributed errors.
- Using randomly generated zero-mean, unit-variance Gaussian pseudo-errors, RMSEs converge to the true standard deviation (SE = 1) once n ≥ 100, with standard deviation within 5% of truth; MAEs converge to 0.8, approximating the expectation of √(2/π). Neither metric is robust at n = 4 or n = 10.
- RMSE satisfies the triangle inequality required for a distance metric: the example in Willmott et al. (2009) (d(a,c)=4, d(a,b)=2, d(b,c)=3) actually represents the MSE, not the RMSE, and the L2-norm proof in Eqs. (5)–(7) shows RMSE does satisfy it.
- RMSE has practical advantages: it avoids absolute values (useful for gradients/sensitivities and data assimilation cost functions) and is generally better at discriminating among model results by weighting unfavorable conditions more heavily.
Methods
- Technical note / commentary design: no new observational dataset; the argument is analytical, using norm theory (L1- and L2-norms linked to MAE and RMSE) and a proof of the triangle inequality for the L2-norm.
- A Monte Carlo-style demonstration: five sets of pseudo-errors of size n = 4, 10, 100, 1000, 10 000, and 1000 000 drawn from a zero-mean, unit-variance Gaussian distribution with different random seeds, comparing RMSEs and MAEs (Table 1).
- Reference to prior empirical example: Chai et al. (2009) reported RMSE-to-MAE ratios of 1.63 to 2.29 for model NO2 column predictions versus SCIAMACHY satellite observations.
Limitations
- Stated by the authors: the analysis assumes unbiased errors and does not consider uncertainties from observation errors or the method used to compare model and observations; all statistics are less useful with limited sample sizes (e.g., n = 4 or 10), where presenting the errors themselves may be more appropriate; for non-normal distributions, additional moments (mean, variance, skewness, flatness) are needed; outliers several orders larger than other samples may justifiably be removed when sample numbers are limited, and systematic errors may need removal before computing RMSEs.
- Evident from the text: the demonstration relies on synthetic Gaussian pseudo-errors rather than real model–observation comparisons, so the convergence results are conditional on the Gaussian assumption; the authors explicitly do not claim RMSE is superior to MAE, so the note offers guidance rather than a definitive metric selection rule.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
14 Own interpretation · 6 No basis given · 4 Supported · 3 Sources not found · 3 Own result · 1 No full text of the sources · 1 Not checked yet
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using hypothetical sets of four errors, Willmott and Matsuura (2005) demonstrated that while keeping the MAE as a constant of 2.0, the RMSE varies from 2.0 to 4.0.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
What the sources say
- Supportedcites Willmott and Matsuura (2005) source
Table 1 identifies five hypothetical sets of four errors, and Section 3 says their RMSE increases as the error magnitudes become more variable. The paper gives the bounds as MAE ≤ RMSE ≤ √n × MAE; with four errors and an MAE of 2.0, those bounds are 2.0 and 4.0. Page numbers are unavailable in our copy. (LLM, conf=0.90)
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In addition, we show that the RMSE satisfies the triangle inequality requirement for a distance metric, whereas Willmott et al. (2009) indicated that the sums-ofsquares-based statistics do not satisfy this rule.”
- Also stated in: § 3 Triangle inequality of a metric · boosted
“This proves that RMSE satisfies the triangle inequality required for a distance function metric.”
- Also stated in: § 4 Summary and discussion · boosted
“In addition, we demonstrate that the RMSE satisfies the triangle inequality required for a distance function metric.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3 Triangle inequality of a metric · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the sample size reaches 100 or above, using the calculated RMSEs one can re-construct the error distribution close to its “truth” or “exact solution”, with its standard deviation within 5 % to its truth (i.e., SE = 1).”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 2 Interpretation of RMSE and MAE
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The authors state this as an assumption: The errors are unbiased and follow a normal distribution when presenting the RMSE.
- The authors state this as an assumption: The uncertainties brought in by observation errors or the method used to compare model and observations are not considered.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For instance, Table 1 shows that neither the RMSEs nor the MAEs are robust when only 4 or 10 samples are used to calculate those values.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 2 Interpretation of RMSE and MAE
plainn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The authors state this as an assumption: The errors are unbiased and follow a normal distribution when presenting the RMSE.
- The authors state this as an assumption: The uncertainties brought in by observation errors or the method used to compare model and observations are not considered.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The RMSE is more appropriate to represent model performance than the MAE when the error distribution is expected to be Gaussian.”
- Also stated in: § 1 Introduction · plain
“When the error distribution is expected to be Gaussian and there are enough samples, the RMSE has an advantage over the MAE to illustrate the error distribution.”
- Also stated in: § 4 Summary and discussion · plain
“We present that the RMSE is not ambiguous in its meaning, and it is more appropriate to use than the MAE when model errors follow a normal distribution.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption: Model errors are likely to have a normal distribution rather than a uniform distribution.
- Also stated in: § 1 Introduction · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Giving higher weighting to the unfavorable conditions, the RMSE usually is better at revealing model performance differences.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 4 Summary and discussion
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“The L1-norm and L2-norm are closely related to the MAE and the RMSE, respectively, as shown in Eqs. ( 3) and ( 4): Horn and Johnson, 1990).”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 3 Triangle inequality of a metric
What the sources say
- Not matchedcites Horn and Johnson, 1990
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“In this technical note, we demonstrate that the RMSE is not ambiguous in its meaning, contrary to what was claimed by Willmott et al. (2009).”
- Also stated in: § 4 Summary and discussion · plain
“We present that the RMSE is not ambiguous in its meaning, and it is more appropriate to use than the MAE when model errors follow a normal distribution.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > Abstract
What the sources say
- Not matchedcites Willmott et al. (2009)
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 4 Summary and discussion · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“One distinct advantage of RMSEs over MAEs is that RM-SEs avoid the use of absolute value, which is highly undesirable in many mathematical calculations.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 4 Summary and discussion
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Similarly, one can readily show that, for several sets of errors with the same RMSE, the MAE would vary from set to set.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 10
- It may state two separate claims as one. 2
- The quote only partly states this claim. 1
Every source the paper cites for this claim was checked and supports it.
In the paper
“They summarized that the RMSE tends to become increasingly larger than the MAE (but not necessarily in a monotonic fashion) as the distribution of error magnitudes becomes more variable.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
What the sources say
- Supportedcites Willmott and Matsuura (2005) source
The Concluding Remarks state the attributed point directly, including the qualification that the increase need not be monotonic. (LLM, conf=0.95)
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“They concluded that the RMSE varies with the variability of the the error magnitudes and the total-error or averageerror magnitude (MAE), and the sample size n.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
What the sources say
- Supportedcites Willmott and Matsuura (2005) source
The Concluding Remarks state that RMSE depends on error-magnitude variability, MAE, and the square root of sample size. The claim says it varies with sample size n, which accurately conveys that dependence without asserting that the relationship is linear. (LLM, conf=0.93)
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Willmott and Matsuura (2005) have simply proved that the RMSE is not equivalent to the MAE, and one cannot easily derive the MAE value from the RMSE (and vice versa).”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
What the sources say
- Supportedcites Willmott and Matsuura (2005) source
Section 3 describes an inconsistent relationship between MAE and RMSE, including cases where RMSE changes with error-magnitude variance. Section 4 explains that RMSE depends on MAE, the distribution of error magnitudes, and the number of errors. This supports the claim that the measures are not equivalent and that one cannot generally derive either value from the other alone. (LLM, conf=0.90)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 1 shows that the MAEs converge to 0.8, an approximation to the expectation of 2 π .”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 2 Interpretation of RMSE and MAE
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
- The authors state this as an assumption: The errors are unbiased and follow a normal distribution when presenting the RMSE.
- The authors state this as an assumption: The uncertainties brought in by observation errors or the method used to compare model and observations are not considered.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When both metrics are calculated, the RMSE is by definition never smaller than the MAE.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The MAE is suitable to describe uniformly distributed errors.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 2 Interpretation of RMSE and MAE
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For other kinds of distributions, more statistical moments of model errors, such as mean, variance, skewness, and flatness, are needed to provide a complete picture of the model error variation.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 4 Summary and discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“The ratio of RMSE to MAE ranged from 1.63 to 2.29 (see Table 1 of Chai et al., 2009).”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
What the sources say
- Not checked — no full text of the sourcecites Chai et al., 2009 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In many of the model sensitivity studies that use only RMSE, a detailed interpretation is not critical because variations of the same model will have similar error distributions.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 4 Summary and discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As every statistical measure condenses a large number of data into a single value, it only provides one projection of the model errors emphasizing a certain aspect of the error characteristics of the model performance.”
- Also stated in: § 4 Summary and discussion · plain
“As stated earlier, any single metric provides only one projection of the model errors and, therefore, only emphasizes a certain aspect of the error characteristics.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Also stated in: § 4 Summary and discussion · plain
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A combination of metrics, including but certainly not limited to RMSEs and MAEs, are often required to assess model performance.”
- Also stated in: § 4 Summary and discussion · plain
“A combination of metrics, including but certainly not limited to RMSEs and MAEs, are often required to assess model performance.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Also stated in: § 4 Summary and discussion · plain
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“While the MAE gives the same weight to all errors, the RMSE penalizes variance as it gives errors with larger absolute values more weight than errors with smaller absolute values.”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The authors state this as an assumption.
The errors are unbiased and follow a normal distribution when presenting the RMSE.
“The underlying assumption when presenting the RMSE is that the errors are unbiased and follow a normal distribution.”
“We also assume the error sample set is unbiased.”
The paper relies on this without support.
Model errors are likely to have a normal distribution rather than a uniform distribution.
“Because model errors are likely to have a normal distribution rather than a uniform distribution, the RMSE is a better metric to present than the MAE for such a type of data.”
The authors state this as an assumption.
The uncertainties brought in by observation errors or the method used to compare model and observations are not considered.
“The uncertainties brought in by observation errors or the method used to compare model and observations are not considered here.”
The paper relies on this without support.
There are often hundreds of observations available to calculate model statistics.
“Fortunately, there are often hundreds of observations available to calculate model statistics, unlike the examples with n = 4 (Willmott and Matsuura, 2005) and n = 10 ( Willmott et al., 2009).”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 4 Summary and discussion
“| 4 | 0.92, 0.65, 1.48, 1.02, 0.79 0.70, 0.57, 1.33, 1.16, 0.76 | |”
§ Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature > 1 Introduction
“When both metrics are calculated, the RMSE is by definition never smaller than the MAE.”
Citations
Cites
Horn, R. A., & Johnson, C. R. (1985) · Cited by 22,203
David, F. N., & Tukey, J. W. (1977) · Biometrics · doi:10.2307/2529486 · Cited by 12,707
Willmott, C., & Matsuura, K. (2005) · Climate Research · doi:10.3354/cr030079 · Cited by 6,512 · cited 4×
“Further, Willmott et al. (2009) concluded that the sums-of-squaresbased error statistics such as the RMSE and the standard error have inherent ambiguities and recommended the use of alternates such as the MAE.”
BackgroundMethodInfluentialHuber, P. J., & Ronchetti, E. M. (2009) · Wiley series in probability and statistics · doi:10.1002/9780470434697 · Cited by 1,823
Ambiguities inherent in sums-of-squares-based error statistics
Willmott, C. J., Matsuura, K., & Robeson, S. M. (2008) · Atmospheric Environment · doi:10.1016/j.atmosenv.2008.10.005 · Cited by 212 · cited 1×
“Fortunately, there are often hundreds of observations available to calculate model statistics, unlike the examples with n= 4 (Willmott and Matsuura, 2005) and n= 10 (Willmott et al., 2009).”
BackgroundMcKeen, S. A., Wilczak, J. M., Grell, G., et al. (2005) · Journal of Geophysical Research Atmospheres · doi:10.1029/2005jd005858 · Cited by 208
Savage, N., Agnew, P., Davis, L. S., Ordóñez, C., Thorpe, R., Johnson, C. E., O’Connor, F. M., & Dalvi, M. (2013) · Geoscientific model development · doi:10.5194/gmd-6-353-2013 · Cited by 128
Taylor, M. H., Lösch, M., Wenzel, M., et al. (2013) · Journal of Climate · doi:10.1175/jcli-d-13-00089.1 · Cited by 93
Chai, T., Kim, H. C., Lee, P., et al. (2013) · Geoscientific model development · doi:10.5194/gmd-6-1831-2013 · Cited by 87
Self-citationA multi-physics ensemble of present-day climate regional simulations over the Iberian Peninsula
Jerez, S., Montávez, J. P., Jiménez‐Guerrero, P., et al. (2012) · Climate Dynamics · doi:10.1007/s00382-012-1539-1 · Cited by 80 · cited 2×
“(2009) (e.g., Taylor et al., 2013; Chatterjee et al., 2013; Jerez et al., 2013).”
Method
Cited by
Sorted by citations
Items 6,601–6,700 of 7,174
Sales, V. F., Racolte, G. E. D. R., Souza, L., Aires, A. S., Lorenz, J., Silva, R., da Silva, L., Dias, R., Mariani, D., Marques, A., et al. (2026) · Minerals · doi:10.3390/min16050479
张, W.-L. 文. Z., & 魏, J.-J. 俊. W. (2026) · The Astrophysical Journal · doi:10.3847/1538-4357/ae5e74
Edwards, K. M., Tehranchi, F., Miller, S., & Ahmed, F. (2026) · Journal of Mechanical Design · doi:10.1115/1.4071835 · Cited by 1
PREVISÃO DE PRODUÇÃO DE CANA-DE-AÇÚCAR UTILIZANDO FRAMEWORK LOW-CODE PYCARET
Calor, P. S., Jr., & Nespolo, R. G. (2026) · Revista Interface Tecnológica · doi:10.31510/infa.v22i2.2371
Temporal Personal Fashion AI System with Multi-Component Integration
Harshani, R., Manamendra, N., Rajapaksha, P., Godaarawa, S., & Harshanath, B. (2026) · International Research Conference on Smart Computing and Systems Engineering (SCSE) · doi:10.1109/scse70081.2026.11499770
Kim, M., Lee, H., Seo, J., Lim, Y., & Park, Y.-G. (2026) · Journal of The Korean Society of Water and Wastewater · doi:10.11001/jksww.2026.40.2.241
Şahin, O., & Çubukçu, B. (2026) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2026.104219 · Cited by 1
Exploring uncertainties across the modelling chain in ML-based streamflow forecastingPreprint
Vinokić, L., Dotlić, M., Dodig, A., Prodanović, V., Kolaković, S., & Stojković, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6737296
Umetani, R., Miyasaka, Y., Souda, H., et al. (2026) · International Journal of Particle Therapy · doi:10.1016/j.ijpt.2026.101319
Wazziki, H. E., & Yousfi, B. E. (2026) · Cereal Research Communications · doi:10.1007/s42976-026-00812-1
Mohamad, S. F. N., Wong, H. M., Tan, G. K. M., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20752-4_31
A Study on Data Acquisition for a Centrifugal Pump using a CFD-based Digital Twin Simulation Model
Park, H.-B., Hwang, J., & Hur, J.-W. (2026) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2026.24.4.19
Global-scale comparison of OLCI remote sensing reflectance from sentinel-3A and -3B
Mélin, F., Cazzaniga, I., & Gossn, J. I. (2026) · Remote Sensing of Environment · doi:10.1016/j.rse.2026.115479
Lee, J. P., & Kim, C. (2026) · Measurement Interdisciplinary Research and Perspectives · doi:10.1080/15366367.2026.2669159
Time Series Prediction of Humidity in Greenhouse Using GRU Neural Network Architectures
Nahedh, S., Kraiem, R., Feki, E., et al. (2026) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset69920.2026.11502220
Wong, H. M., Chan, L. L., Khoo, L. J., & Perumal, S. (2026) · IEEE International Conference on Robotics and Technologies for Industrial Automation (ROBOTHIA) · doi:10.1109/robothia68364.2026.11507075
Kshatri, D. S., Mishra, S., Dewangan, P., et al. (2026) · Chemical Papers · doi:10.1007/s11696-026-04946-8
Torres, C. G. S., López, M. I. M., Sereno, H. I., et al. (2026) · Journal of Asian Ceramic Societies · doi:10.1080/21870764.2026.2672837
Méndez, D. P., Niño, B. C., Pérez‐Sánchez, M., et al. (2026) · Journal of Environmental Management · doi:10.1016/j.jenvman.2026.129927
Wang, G., Zhu, L., 万鲁峰, et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115438
Sermlao, P., Pannucharoewong, N., Rattanadecho, P., et al. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.110952
An Anchor Point–Assisted Image-Matching Method for Weakly Textured Scenes Using Structured Features
Chen, M., Shi, J., Ma, Z., et al. (2026) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.26-00014r2
Zhao, Y., Liu, J., Zhang, X., et al. (2026) · Water · doi:10.3390/w18101174
Wani, S. R., Al‐Fakih, A., & Panghal, H. (2026) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2026.104189
Data Structure-Aware Ensemble Modeling for Time-Series Prediction: A Case Study of Sewage Generation
Lee, J.-H., Kim, C. H., Shin, J.-H., et al. (2026) · Applied Sciences · doi:10.3390/app16104842
Islam, M. T., Nishat, A., PARTHO, D. K., et al. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.110970
Tian, R., geng, X., Li, M., & Zhang, P. (2026) · Molecular Diversity · doi:10.1007/s11030-026-11560-z
Machine learning-based modeling of watershed drainage density in different climates
Chapi, K., Sarbazi, M., Fatehi, Z., et al. (2026) · Modeling Earth Systems and Environment · doi:10.1007/s40808-026-02819-3
Deep learning-based stock market forecasting: A comparative analysis of ANN, CNN, and LSTM
M, C. C., Hawaldar, I. T., Vinish, P., Pinto, P., & Shetty, C. (2026) · Investment Management and Financial Innovations · doi:10.21511/imfi.23(2).2026.17 · Cited by 1
Wang, J., Zhang, J., Zhang, Z., et al. (2026) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2026.148501
Nature, economy and mental health: Predictive insights from historical language patterns
Richardson, M. (2026) · Journal of Environmental Psychology · doi:10.1016/j.jenvp.2026.103078
Shubert, I., Poehlein, E., Ashana, D. C., Kuchibhatla, M. N., Gallis, J. A., Olsen, M. K., Porter, L. S., Moss, M., Hough, C. L., & Cox, C. E. (2026) · CHEST Critical Care · doi:10.1016/j.chstcc.2026.100279
Prediction of specific penetration resistance of clayey soils
Geem, Z. W., Bekdaş, G., Ni̇gdeli, S. M., et al. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-41481-7.00014-6
Wang, S., Zhang, S., Yin, H., et al. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.05.014
Abbas, A. F., Khaleel, Y. L., Habeeb, M. A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23219-9_42
Mansur, L. K., Bernawis, L. I., Vicario, A. D., et al. (2026) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1624/1/012009
Li, J., Zhao, X., & Yin, Y. (2026) · Science and Technology for the Built Environment · doi:10.1080/23744731.2026.2665560
CTRL: Cross-Modal Transformer With Reinforcement Learning for Climate Causal Discovery
Liu, J., Wang, T., Lu, Y., & Ji, J. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3688211
Kim, S., Kim, H., Lee, S. H., & Hong, J. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112606 · Cited by 1
Blue Carbon Modeling of Mangrove Forests in Muara Gembong Using the InVEST Model
Jaelani, A., Ankiq Taofiqurohman, S., & Astuty, S. (2026) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1624/1/012003
Si, Y., Yu, J., Li, G., Carrera, J., Jin, J., & Haihua, B. (2026) · Plants · doi:10.3390/plants15101542
Omio, M. H., Mollah, A. S., & Mahmud, K. (2026) · Health Physics · doi:10.1097/hp.0000000000002149
Vishwakarma, S. K., Kothari, K., & Pandey, A. (2026) · Modeling Earth Systems and Environment · doi:10.1007/s40808-026-02820-w
Comparative Study of Sentiment Analysis Models of ANTAM Shares Based on Platform X Reviews
Immanuel, J., & Mauritsius, T. (2026) · doi:10.1109/eect68756.2026.11517745
Automatic Grading of Chinese as a Second Language Reading Texts Based on Multi-LLM Weighted Voting
Han, X., & Xu, J. (2026) · International Conference on Educational and Information Technology · doi:10.1109/iceit68991.2026.11521725
Karadut, O., Aliyev, J., Romero, C. E., Yao, Z., Saro, R. D., & Craparo, J. (2026) · ACS Omega · doi:10.1021/acsomega.6c03040
A hierarchical generative framework for the computational re-animation of Dunhuang dance
Zhang, Q., Feng, S., Xu, X., et al. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07681-3
Pizzi, L. M., Balsamello, C., Ambrosini, A., Colturi, C., Grosse, P., Jovane, C., Magatti, M., Melfa, G., Pianca, S., Ruinelli, L., et al. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105058
Yüksel, O., Bayraktar, M., & Nuran, M. (2026) · Ships and Offshore Structures · doi:10.1080/17445302.2026.2672462
Histogram tabanlı gradyan artırma yöntemi ile Türkiye için kısa vadeli elektrik talep tahmini
Karamollaoğlu, H. (2026) · Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.28948/ngumuh.1817112
Sari, M., Genç, G., Temiz, I., et al. (2026) · Textile Research Journal · doi:10.1177/00405175261449432
Guo, W., & Mu, L. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3693879
Industry 4.0 Based on Real-Time Process Monitoring and Control for Sustainable Bioethanol Production
Nayak, K. K., Sahu, R., Zafar, M., et al. (2026) · Clean Energy Production Technologies · doi:10.1007/978-981-95-9690-4_12
Machine Learning-Driven Techno-Economic Uncertainty Analysis in Batch Pharmaceutical Manufacturing
Rueda-Ordóñez, D. A., Mesquita, L. C. D. S., & Brandão, A. L. T. (2026) · ACS Omega · doi:10.1021/acsomega.5c09455
Predicting Tunneling-Induced Ground Settlements Using Machine Learning Techniques
Agarwal, J., Manchanda, H., & Agarwal, V. (2026) · Lecture notes in civil engineering · doi:10.1007/978-981-95-7956-3_20
Hajibolouri, E., Khanjani, M., Pal, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6820189
Lak(aln159@uregina.ca), A., Mehrandezh, M., Stilling, D. S. D., et al. (2026) · Precision Agriculture · doi:10.1007/s11119-026-10366-1
Khoshru, A. S., & Younesian, D. (2026) · Building Acoustics · doi:10.1177/1351010x251412548
Samsuri, S., SIPAHUTAR, R. A., Zaitunah, A., et al. (2026) · Asian Journal of Forestry · doi:10.13057/asianjfor/r100131
Bayesian spatial Durbin modelling of stunting prevalence across Indonesian districts
Yanuar, F., Asdi, Y., Sandi, S., et al. (2026) · Geospatial health · doi:10.4081/gh.2026.1441
Sangkaphet, P., Chansiri, N., Kaewklom, C., et al. (2026) · Applied Sciences · doi:10.3390/app16115308
An empirical analysis of explainable artificial intelligence tool for solar radiation prediction
Santona, C. F. T., Sharmin, N., Sevas, M. S., Islam, R., & Sagor, S. R. (2026) · Discover Geoscience · doi:10.1007/s44288-026-00554-x
Huang, F., Luo, Y., Chen, H., Meng, Y.-H., Li, W., Liang, H., & Ai, C. (2026) · Archives of Toxicology · doi:10.1007/s00204-026-04447-3
Mathonsi, M., Mbuli, N., & Motepe, S. (2025) · IEEE AFRICON · doi:10.1109/africon66545.2025.11533756
Saravanakumar, R., Jain, R., Bharadwaj, A., et al. (2026) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-026-02426-w
Patra, R., Basu, T., & Mondal, B. K. (2026) · Deltas of the world · doi:10.1007/978-3-032-16261-8_1
Oduori, G., Cocco, C., Sajadi, P., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6839558
Muzhofar, H. A., Nusantara, C. A. D. S., Khomsin, et al. (2026) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1628/1/012042
Rakotoarivelo, T., & Malet-Damour, B. (2026) · Building and Environment · doi:10.1016/j.buildenv.2026.114777
Reguig, M., Mokaddem, A., Belkheir, M., et al. (2026) · SN Computer Science · doi:10.1007/s42979-026-05091-5
Öttl, M. A., Schwiersch, N., Lesny, K., et al. (2026) · Cogent Engineering · doi:10.1080/23311916.2026.2678633
Zhang, J., Chen, X., Song, H., Zhang, H., Zhu, G., Teng, Y., & Shi, J. (2026) · Marine and Coastal Fisheries · doi:10.1093/mcfafs/vtaf048
Assessment of a Fine-Tuned Vision-Language-Action Model for Robotic Feature-Following Inspection
Krüger, M., Salem, M., & Reischl, M. (2026) · Neural Processing Letters · doi:10.1007/s11063-026-11860-3
A dataset of NDVI predictions for the Qinghai-Tibet Plateau based on CMIP6 (2025–2100)
ZHANG, Z., Fenggui, L. I. U., Zhi, Z., et al. (2026) · China Scientific Data · doi:10.11922/11-6035.csd.2025.0093.zh
Savran, E. (2026) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070261454760
Field-Validated Accelerometer-Based Tension Estimation for Overhead Distribution Lines
Kim, J. H. (2026) · IEEE Transactions on Power Delivery · doi:10.1109/tpwrd.2026.3697749
Comparative data-driven prediction of thermal performance of cylindrical lithium-ion battery packs
Kirkar, M. O. (2026) · Applied Thermal Engineering · doi:10.1016/j.applthermaleng.2026.131677
Prediction of Digestible and Metabolizable Energy in Swine Feed Using Machine Learning
Yu, J.-W., Liu, S.-H., Ye, D.-X., et al. (2026) · ACS Omega · doi:10.1021/acsomega.6c03545
Musa, M. A., Suharyanto, A., Lalasari, L. H., Ichlas, Z. T., & Mubarok, M. Z. (2026) · Journal of Sustainable Metallurgy · doi:10.1007/s40831-026-01541-9 · Cited by 1
Kazmi, S. A., Khan, M. S., Bilal, M., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0348881
Tokgöz, S., Açıkkar, M., & Aydın, B. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537229
Cabeza-Ramírez, L. J., Puccia, A., Tabales, J. M. N., et al. (2026) · The International Journal of Management Education · doi:10.1016/j.ijme.2026.101474
Binen, T., Özıç, M. Ü., & Çetin, S. (2026) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/ichora69329.2026.11537152
AI-driven seasonal streamflow prediction in Victoria: a focus on ENSO climate predictor
Bani, S., Hossain, I., Imteaz, M. A., et al. (2026) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-026-03256-5
Vu, N. D., & Huyen, N. T. (2026) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1633/1/012008
Performance of global climate models in assessing the Indian monsoon: A systematic evaluation
Dash, Y., Gupta, V., Abraham, A., et al. (2026) · Physics and Chemistry of the Earth Parts A/B/C · doi:10.1016/j.pce.2026.104565
Learned Response-Field Inertia Operator for HEC-RAS 2D Water-Surface Elevation PredictionPreprint
Holmberg, E. A., Ioup, E., Ferdaus, M. M., Abdelguerfi, M., & Simeonov, J. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7268529 · Cited by 2
Evaluation of Wind Energy Potential of Bolu Province Using Weibull Distribution
Erdoğan, B., Güneş, A., & Karaoğlu, A. (2026) · Karadeniz Fen Bilimleri Dergisi · doi:10.31466/kfbd.1755266
Zheng, W., Guo, Q., Cheng, Z., et al. (2026) · Remote Sensing · doi:10.3390/rs18111859
M., S. S., Paliwal, V., & Lavanya, B. (2026) · Water Resources Management · doi:10.1007/s11269-026-04597-0
Estimating ML-driven compressive strength of geo-polymer stabilized soils
Murtaza, R. S., Sultana, N., Debanath, O. C., & Rahman, M. A. (2026) · Discover Civil Engineering · doi:10.1007/s44290-026-00524-9 · Cited by 1
Detection of Environmental Tobacco Smoke Using a Multi-Sensor Array Integrated E-nose
Wu, Y., Zhang, L., & Deng, Z. (2026) · International Conference on Sensors and Information Technology (ICSI) · doi:10.1109/icsi70302.2026.11545177
IoT Enabled Solar Powered Automation and Monitoring System for Modern Poultry Farming
Hassain, M. M., Hoque, M. M., Nandy, R., et al. (2026) · SN Computer Science · doi:10.1007/s42979-026-05140-z
An Ensemble Approach for data forecasting from Knowledge Assimilation
Singh, A. K., Abrol, V., Gambhir, A., et al. (2026) · doi:10.1109/icass69550.2026.11547540
Wang, L., Chen, W., Lu, L., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6903431
Diseño de un sistema de monitoreo térmico para la asistencia en la deposición de material en WAAM
Ramirez, U. M. (2025) · Apuntes de Ciencia e Ingeniería · doi:10.37511/apuntesci.v4n2a4
Hugo, M. Á., Rubio, C. A. N., Moreno, J. G. R., Araiza, J. L. R., Carrillo-Serrano, R. V., Aparicio, M. G., González-García, I., & Perea, M. T. (2026) · Mathematics · doi:10.3390/math14122056
刘海旭, Liu, W., Wang, Z., et al. (2026) · International Conference on Information Science, Electrical and Automation Engineering (ISEAE) · doi:10.1109/iseae69422.2026.11544377
Riva, E., Ponti, S., & Guglielmin, M. (2026) · Journal of Geovisualization and Spatial Analysis · doi:10.1007/s41651-026-00269-0
Metadata
- Authors
- Chai, T., & Draxler, R. R.
- Affiliations
- National Oceanic and Atmospheric Administration (US)
- Venue
- Geoscientific Model Development
- Publisher
- Copernicus GmbH
- Published
- 2014-06-30
- Volume
- 7
- Issue
- 3
- Pages
- 1247-1250
- ISSN
- 1991-959X (ISSN-L)
- 1991-9603
- OpenAlex
- W2102148524
- Semantic Scholar
- 8c42db1839098b46f18265907464c16e49bb7a1c
- Cited by
- 7,178
- References
- 12
- Citations by year
- 2026: 1015 · 2025: 1120 · 2024: 980 · 2023: 873 · 2022: 751 · 2021: 683 · 2020: 538 · 2019: 411 · 2018: 324 · 2017: 235 · 2016: 175 · 2015: 59 · 2014: 13
- FWCI
- 106.31
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Geoscientific model development (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Oceanic and Atmospheric Administration (NA09NES4400006)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations
- Physical Sciences › Environmental Science › Water Science and Technology › Hydrology and Watershed Management Studies
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Keywords
- root mean square error, mean absolute error, model evaluation metrics, error distribution, Gaussian errors, triangle inequality, distance measures, model evaluation, hydrological model evaluation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-17, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-17 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
