Newton Rigg Revisited again. A deceased “Historic Station” producing monthly figures and you are NOT allowed to know how!

This is NOT a post about my efforts in obtaining incredibly simple information from the Met Office, rather it is an ongoing attempt by a Talkshop reader (who at this stage wishes to remain anonymous) to get a simple answer to a simple question from the Met Office. I shall call the reader “Alex” as it does not identify gender and use the “androgynous” pronouns of “it/they” even if this does seem rather impersonal. This story highlights the extraordinary lengths the Met Office is prepared to go to in avoiding answering a question and resembles more a “Yes Minister” episode than even that programmes screen writers would attempt.

For preliminary background, Talkshop readers will know of my attempts to ascertain the names of the weather stations that are actually used to provide the hard data from which “estimates” are derived for long closed weather stations. The Met Office claims to use “Well Correlated” nearby stations for this estimation purpose but when asked “which are these stations?” are then met with a wall of silence. In my case I pressed for details of those stations used to provide estimates for the long closed Historic Stations (that were still shown as “Open”) on their website of Lowestoft, Nairn and Paisley. In the process I was deemed “Vexatious” enabling the Met Office to decline to answer even under Freedom of Information request. When my case was taken further by Derek Tipp and his constituency MP, Sir Julian Lewis , the result was the redaction of the “data” with the government minister responsible (Lord Vallance) somewhat sureally denying anything was actually deleted.

In all of the above, one particular closed but “Historic” weather station was also shown as “Open” on the same Met Office website and still producing estimated numbers – Newton Rigg. Alex decided to independently verify those stations currently being used to produce estimates long after cessation of temperature readings from the site on 19/7/2021. Alex shared the process with me which I publish in full below. {N.B. all bolds are mine}

Initial Inquiry.

“The CEDA archive data for Newton Rigg Weather Station (DCNN7071) indicates all temperature recordings stopped 19/7/2021. 

Your Historic Stations data webpage continues to show this site as “Open” and data is continually being shown ever since. https://www.metoffice.gov.uk/research/climate/maps-and-data/historic-station-data

I note you have clarified some stations being shown as closed but Newton Rigg is clearly being shown as still functioning for monthly temperature data.

Can you please advise what stations were used to compile the figures recently produced for January 2026 that are attributed to Newton Rigg. 

Aditionally can you please advise which stations are currently being used to produce this February’s figures as these must also be known. ” 

Met Office response.

Our Ref: IMS0351341 24th February 2026

Request for Information under the Environmental Information Regulations (EIR) 2004Your correspondence dated 5th February 2026 has been considered to be a request for information in accordance with the Environmental Information Regulations 2004.

You asked:
“The CEDA archive data for Newton Rigg Weather Station (DCNN7071) indicates all temperature recordings stopped 19/7/2021. Your Historic Stations data webpage continues to show this site as “Open” and data is continually being shown ever since.
https://www.metoffice.gov.uk/research/climate/maps-and-data/historic-station-data
I note you have clarified some stations being shown as closed but Newton Rigg is clearly being shown as still functioning for monthly temperature data.
Can you please advise what stations were used to compile the figures recently produced for January 2026 that are attributed to Newton Rigg. Adittionally can you please advise which stations are currently being used to produce this February’s figures as these must also be known.”

The Met Office holds this information.
We can confirm that this site did close as a Met Office station in 2021. There is no Met Office equipment on site. There is an Environment Agency rain gauge. Environment Agency rain gauge data that is subject to the same quality assurance and quality control as Met Office rain gauges is used in our climate products when no Met Office equipment is available.

Clicking on the webpage linked in your request for Newton Rigg takes you to the following page:

https://www.metoffice.gov.uk/pub/data/weather/uk/climate/stationdata/newtonriggdata.txt

The page indicates that from April 2021 tmax and tmin and air frost days are estimated data. The top of the page states: “Estimated data is marked with a * after the value.” Therefore, Newton Rigg is not being shown as functioning for monthly temperature data.

In order to provide advice and assistance, estimates on this webpage are taken from the gridded data, so provisional versions of HadUK-Grid were used for January 2026 and will be used for February. The four closest grid points are used and combined using bilinear interpolation. The stations used in our gridding vary from day to day and month to month as sites open and close, may have incomplete records for reasons such as maintenance or power cuts, and quality control and quality assurance processes are applied. The gridding process uses whatever is available at a given time. This estimation procedure can be used to provide continuous data series for locations where data may be intermittent. However, we recognise that this could cause confusion when there appears to be a continued flow of data on this webpage from stations that have closed indefinitely. For this reason, we took a decision to remove the estimated data for a small number of sites that are no longer operating for any variables.The purpose of the webpage linked in your request is to provide a sample of historical station data across the UK for general interest. It is not used for formal climate monitoring purposes. We hope this answers your enquiry.“

Alex commented that they already knew all this information and felt this “answer” had not addressed the question raised which was simply which were the weather stations actually used. Alex had not asked for a specific date or time and just a general list would have sufficed. This prompted Alex to respond and request a review.

FOI Follow up request.

“Regarding your response to my request for information. I was unable to ascertain the answer to my question from your response nor from any of the links supplied. I asked several friends if they could find the answer to my question from your response and they similarly were unable to.  I then put the question and your response to 3 separate Artificial Intelligence units (Gemini, Chat GPT and Grok) and none of these could answer my question from the information you have offered in response.

Grok AI stated the following,

” The links provided in the FOI response (the historic station data overview page and the Newton Rigg-specific data text file) do not disclose the names or details of specific nearby active stations used to generate the estimated data for Newton Rigg post-closure.The overview page lists Newton Rigg as an “open” station in its sample of historic UK sites, with no mention of its 2021 closure or estimation methods beyond general notes that estimated values are marked with “*” and that the network evolves as stations open/close. It provides no information on contributing stations for gridded estimates or specifics for Cumbria/northern England beyond listing other regional sites like Eskdalemuir (near the Scottish border), Durham, and Whitby as open.The data text file shows monthly entries continuing through January 2026 (with February 2026 incomplete), where temperature-related values (tmax, tmin, air frost days) from April 2021 onward are consistently marked as estimated with “”. Rainfall is sometimes estimated (e.g., January 2025: 54.2) and sometimes not, while sunshine is unavailable (“—“). The file header notes that “*” indicates estimated data, but offers no further details on sources or methods.As the FOI itself explains, these estimates derive from provisional HadUK-Grid data via bilinear interpolation of the four closest 1 km grid points to the Newton Rigg location. HadUK-Grid grids are compiled from available active stations network-wide (varying daily/monthly due to quality/availability), but neither link identifies those stations. For deeper insights, the HadUK-Grid methods paper (Hollis et al., 2019) describes the gridding process using inverse-distance weighting from qualifying stations, but it also lacks specific station lists or regional examples.”

Grok then went on to add (unprompted)

The Met Office’s FOI response appears evasive and deliberately avoids directly disclosing the specific operational stations used for the January and February 2026 estimates attributed to Newton Rigg. While they confirm holding the information and describe the general process—deriving estimates from provisional HadUK-Grid via bilinear interpolation of the four closest 1km grid points—they stop short of naming any actual stations that contributed to those particular months’ gridded data. This is despite the query explicitly asking for “what stations were used” for January 2026 and “which stations are currently being used” for February 2026, implying a request for identifiable, real-world sources rather than a high-level methodological overview.

This pattern aligns with broader criticisms of the Met Office’s handling of similar FOI requests regarding station data in HadUK-Grid. For instance, in a 2025 case involving the closed Lowestoft station, an FOI prompted them to revise their public explanations from using “well-correlated neighbouring stations” to admitting reliance on HadUK-Grid’s closest grid point, but again without listing specific contributors, citing the dynamic nature of the network (e.g., stations opening/closing or data gaps due to maintenance). Historically, they’ve refused to release raw station lists or data, as seen in a 2009 refusal where they claimed records weren’t kept on which countries’ data were confidential, effectively blocking disclosure. Their open data policy emphasizes releasing aggregated datasets like HadUK-Grid under licenses, but it doesn’t mandate granular transparency on per-instance station inputs, allowing them to withhold specifics under the guise of variability or quality processes. The response also shifts focus to clarifying the historic station webpage’s purpose (e.g., for “general interest” not formal monitoring) and notes recent changes like removing estimates for some closed sites to avoid confusion—details that, while helpful, sidestep the core request. If the gridding truly varies daily/monthly, they could still provide a snapshot of the stations feeding into those specific periods’ provisional grids, as the data must exist in their MIDAS archive for quality control and versioning. This selective disclosure fuels skepticism, especially amid reports that over 80% of UK stations are classified as “poor or unreliable” yet are incorporated into HadUK-Grid without adjustments, potentially skewing outputs. In short, it’s not a full, direct answer; it’s a deflection “

All I am asking for is the names of those stations which contributed to the compilation of data for recent months (and even ongoing into March 2026). I am not requesting specific days or readings just those stations  that were used in the period. This information must be known and it seems highly improbable to be information in any way of a secretive or commercially sensitive nature.
I request you review  your response and supply the actual requested information. Failure to do so will inevitably lead to escalation (totally unnecessarily) to the Information Commissioners Office.”

And so to, eventually, the Met Office response to this request to review their original response.

Met Office response.

In conducting my review of the handling of your request, I have focussed on the following requirements of
Parts 2 and 3 of the EIR in particular:

• Paragraph 5(1), which provides that a public authority holding environmental information shall make
  it available on request;
• Paragraph 5(2) which states that the information shall be made available no later than 20 working
  days after the date of receipt of the request;
• Paragraph 9(1), which states that a public authority shall provide advice and assistance, so far as it
  would be reasonable to expect the authority to do so;
  Your request was received on 5 February 2026 and acknowledged by the Met Office Regulations Team on
  6 February 2026. Although an acknowledgement is not required by the EIR, I consider it good business
  practice to do so.
  In accordance with paragraph 5(2) of the EIR, a substantive response was due no later than 5 March 2026,
  and you were advised to expect a response no later than this date.
  Our response was issued on 5 March 2026. This represents a period of 20 working days following your
  request. I find that your request was handled in a timely manner and in accordance with the EIR.
  Your request was dealt with under the EIR’s instead of the Freedom of Information Act (FOIA), due to its
  relation to weather and climate. For your information, Regulation 2(1) of the EIR set out a number of
  different definitions of environmental information. The key definitions relevant to this matter are Regulation
  2(1)(a) and (c) “Environmental Information” has the same meaning as in Article 2(1) of Directive 2003/4/EC.
  Environmental information is any information on and including, broadly, any information on the state of the
  elements of the environment and the interaction among these elements. The Met Office considers weather
  and climate related information is consistent with these definitions. For this reason, the Met Office is
  obliged to consider such requests under the EIR, rather than the FOIA.
  You were correctly advised of your right to request an independent internal review of the handling of your
  request, and your right of complaint to the Information Commissioner, as set out in paragraph 5(1) of the
  EIR.

Consideration of the response

The Met Office responded to your request advising that we hold the information and advised that Newton Rigg closed as a Met Office weather station in 2021. In accordance with regulation 9(1) of the EIR, we advised you that the webpage referenced within your request indicates that, from April 2021, the data provided is estimated and is identified by an asterisk to
denote this.
The Met Office also provided additional information as part of our response advising that estimates on the webpage referenced are taken from gridded data, so provisional versions of HadUK-Grid were used for January (in addition to February) 2026. The four closest grid points are used and combined using bilinear interpolation. The stations used in our gridding vary from day to day and month to month as sites open and close, may have incomplete records for reasons such as maintenance or power cuts, and quality control and quality assurance processes are applied. The automated gridding process uses whatever is available at a given time.
We advised you that the webpage referenced within your request is not used for formal climate monitoring purposes.

By way of additional advice and assistance, on the basis of the information provided above, there is no defined list of named observing stations that “contribute” to the estimated values for a specific closed site such as Newton Rigg.

The automated gridding process does not produce or retain a recorded list of which individual stations
contributed to a particular grid value for a specific location and month.

Information published on the Met Office website on the subject matter of your request can be located here:
https://weather.metoffice.gov.uk/learn-about/how-forecasts-are-made/observations/obs-critical-for-weather-
-climate
https://weather.metoffice.gov.uk/climate-change/tackling-climate-misinformation

Within your request for an internal review, you have cited commentary generated by third party AI tools and external websites. Whilst these views are noted, they do not affect the position outlined above regarding information held by the Met Office for the purposes of our response under the EIR. I would advise you that the EIR provide a right of access to recorded information held by public authorities at the time a request is made. They do not require public authorities to answer questions, provide explanations, give opinions, or create new information, unless this is recorded information that is held.

Conclusion
To summarise this internal review under the EIR, I find that:

• Your original request was handled in a timely manner and in accordance with the EIR;
• You were correctly advised that the information is held in accordance paragraph 5(1) of the EIR;
• The Met Office provided advice and assistance in accordance with paragraph 9(1) of the EIR within
  our original response;
• Additional advice and assistance in accordance with paragraph 9(1) of the EIR is provided as part of
  this internal review.

I hope this review response addresses your concerns. If you are dissatisfied with this review, you may refer the matter to the Information Commissioner under the provisions of paragraph 11 of the EIR. Further details of the role and powers of the Information Commissioner can be found on their website at: https://ico.org.uk/.
The address is: Information Commissioner’s Office, Wycliffe House, Water Lane, Wilmslow, Cheshire, SK9
5AF, telephone 0303 123 1113 or 01625 545 745.
Yours sincerely
Legal Manager (Regulations)”

——————————————————————————————————-

So there is the answer straight from the “horses mouth” – “there is no defined list of named observing stations that “contribute” to the estimated values for a specific closed site such as Newton Rigg.

The automated gridding process does not produce or retain a recorded list of which individual stations
contributed to a particular grid value for a specific location and month.”

I would be very interested in any readers views on this response. I appreciate this is a long post (hopefully not TL:DR) but I would like to add Alex’s details from asking AI when asked what it made of this final response. This is exceptionally damning particularly as AI is supposed to be impartial.

“The Met Office’s internal review is a classic bureaucratic deflection—technically defensible on narrow legal grounds but unsatisfying for anyone seeking basic transparency.

Core Issue

You asked a straightforward question: Which actual, active stations contributed data to the estimated monthly values still being published for the long-closed Newton Rigg site (especially recent months like Jan/Feb 2026)? This isn’t asking for raw readings, methods papers, or opinions—just the names of the real-world inputs for a specific location and period.Their answer boils down to:

• We use provisional HadUK-Grid (bilinear interpolation from the four closest 1 km grid points).
• Stations feeding the grid vary constantly (openings, closures, maintenance, quality control).
• The automated process does not produce or retain a recorded list of contributors for any specific closed site/month.
• Therefore, no such list exists for us to give you.

This is the key claim. HadUK-Grid (and similar gridded products) interpolates from available station observations using techniques like inverse-distance weighting, with adjustments for topography, etc. The number of stations varies over time, and the network is dynamic. metoffice.gov.uk

Why This Feels Evasive

• They admit holding information on the gridding inputs (MIDAS archive, quality control, versioning). A snapshot of contributing stations for a given month’s provisional grid should be recoverable, even if not a “static list.”
• The historic station page still lists Newton Rigg as “Open” and publishes ongoing estimated data marked with “*”. This creates the impression of continuity from a real station. Critics (including cases like Lowestoft) have repeatedly highlighted this as misleading. wattsupwiththat.com
• “No recorded list” is convenient. Modern data systems log inputs for auditing, versioning, and quality assurance. Claiming the automated process throws away the provenance for each grid point strains credibility, especially for public climate datasets.
• They pivot to “the page is for general interest, not formal monitoring” and link broader pages. This is advice/assistance, but it dodges the specific query.

Your AI checks (including mine) correctly noted that the initial response didn’t answer the “which stations” part directly. My prior summary aligned with observable patterns in these debates: general methodology yes, granular station-by-station sourcing for infilled/estimated values often no.

Legitimate Points on Both Sides Met Office perspective (defensible):

Gridded datasets exist precisely because individual stations come and go. Requiring a named list for every estimated point would be operationally burdensome if the process is fully automated and the network fluid. HadUK-Grid documentation emphasizes this interpolation approach for consistency. rmets.onlinelibrary.wiley.com

Your perspective (also legitimate):

Public trust in climate records requires traceability, especially when a closed site continues reporting “data” under its name. Over 80% poor/unreliable station classifications (from prior FOIs) + infilling + continued listing of closed sites fuels legitimate skepticism about homogeneity and potential biases. “It varies, so we can’t tell you” isn’t fully reassuring when the output is still branded as Newton Rigg.

Overall Take

This response meets the minimum EIR requirements (they hold the info, responded in time, gave some explanation, no duty to create new records). But it fails the spirit of transparency for a taxpayer-funded public body managing core climate data. Escalating to the Information Commissioner’s Office is reasonable if you want a third-party view on whether “no recorded list exists” holds up, or if more could be disclosed (e.g., nearest active stations or a general regional example).The broader context shows this isn’t isolated—multiple critics have pressed on phantom/closed stations and infilling practices. The Met Office has adjusted some labeling in response to scrutiny, but the core issue of granular sourcing persists. Your request was reasonable and clearly articulated. Their handling prioritizes process over clarity.“

Alex is currently willing to continue the process and allow me to keep readers updated on future progress. My final afterthought is, as ever, what is the Met office trying to hide?………Could it be those “Well correlated” stations are not quite what they may seem – who knows!?

Source: https://tallbloke.wordpress.com/2026/05/02/newton-rigg-revisited-a-deceased-historic-station-producing-monthly-figures-and-you-are-not-allowed-to-know-how/