Create classifier for Costa Rica moths

[JennaLawson]

Provisional list for Costa Rica Lepidoptera
Lepidoptera of Costa Rica.xlsx

[LevanBokeria]

Hi @JennaLawson and @DavidRoy. Just want to very quickly confirm this:

• there are two rowz where "Subspecies" entry is corrupted I think. Row 7920 has "zyzyxoxyx" and row 4476 says "(aggr.). I will remove these Subspecies entries.
• Whenever subspecies are specified, we should download images only for those subspecies, right? And not the whole species?

[DavidRoy]

@LevanBokeria I recommend ignoring the subspecies and just using the list of names at the species level

[LevanBokeria]

Thanks @DavidRoy.

I've uploaded the google sheet for Costa Rica list in this folder.

There are quite a few missing species on GBIF unfortunately. Please fine them by filtering the "status" column for "NotAvail".
Also, please check the fuzzy matches by filter the "match_type" column for "FUZZY".

I will meanwhile download images for thos species that are available on GBIF.

[JennaLawson]

Hi Levan, Thank you for this, I'll make a summary of what is missing and will share this with colleagues in Costa Rica with the hope that maybe some images can be added. If images are added is it an easy process to extract them? Best wishes Jenna

…

________________________________ From: Levan Bokeria ***@***.***> Sent: 23 October 2023 11:40 To: AMI-trap/on_device_classifier ***@***.***> Cc: Jenna Louise Lawson ***@***.***>; Mention ***@***.***> Subject: Re: [AMI-trap/on_device_classifier] Create classifier for Costa Rica moths (Issue #28) CAUTION: This email originated from outside of the organisation. Do not click links or open attachments unless you recognise the sender and know the content is safe. Thanks @DavidRoy<https://github.com/DavidRoy>. I've uploaded the google sheet for Costa Rica list in this folder<https://drive.google.com/drive/folders/1K0V0myudrZtKxddGxm1U_Gm9qv_CsCEa?usp=share_link>. There are quite a few missing species on GBIF unfortunately. Please fine them by filtering the "status" column for "NotAvail". Also, please check the fuzzy matches by filter the "match_type" column for "FUZZY". I will meanwhile download images for thos species that are available on GBIF. — Reply to this email directly, view it on GitHub<#28 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AY7MMXNVMZ74244GPQ4IPIDYAZCTVAVCNFSM6AAAAAA5F57LTWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONZUHEYTIOBQGU>. You are receiving this because you were mentioned.Message ID: ***@***.***> This email and any attachments are intended solely for the named recipients and are confidential. If you are not the intended recipient, please reply to the email to highlight the error and delete this email from your system; you must not use, disclose, copy, or distribute this email or any of its attachments. UK Centre for Ecology & Hydrology (UKCEH) has taken reasonable precautions to minimise risk of this email or any attachments containing viruses or malware, but the recipient should carry out its own virus and malware checks before opening the attachments. UKCEH does not accept any liability for any losses or damages which the recipient may sustain due to presence of any viruses. Opinions, conclusions or other information in this message and attachments that are not related directly to UKCEH business are solely those of the author and do not represent the views of UKCEH. We process your personal data in accordance with our Privacy Notice, available on the UKCEH website. https://www.ceh.ac.uk/privacy-notice Registered office address; Maclean Building Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire, United Kingdom, OX10 8BB Companies Registered Name; UK Centre for Ecology & Hydrology Place of Registration; England Registered Company Number; 11314957

[LevanBokeria]

Hi @JennaLawson

You mean if they add images to GBIF, correct? I think it should be straightforward to download new images, yes. If they do upload anything, let us know and we'll download them (or I suppose @KatrionaGoldmann will :) )

[LevanBokeria]

By the way, @JennaLawson GBIF has this neat online tool you can use to check for species in the GBIF backbone:
https://www.gbif.org/tools/species-lookup

Our code (adapted from Rolnick) just uses the API version of this. But if you yourself would like to dynamically check any given species checklist, that page is quite useful. It will highlight missing species, and even give you multiple alternative match options for species that couldn't be matched. Its quite good for exploration.

[JennaLawson]

Amazing thanks Levan. Yes to add to GBIF. I checked those not on there and considering how many species there were I didn't think the missing numbers were too bad. Best wishes Jenna Sent from Outlook for Android<https://aka.ms/AAb9ysg>

…

________________________________ From: Levan Bokeria ***@***.***> Sent: Tuesday, October 24, 2023 4:55:13 PM To: AMI-trap/on_device_classifier ***@***.***> Cc: Jenna Louise Lawson ***@***.***>; Mention ***@***.***> Subject: Re: [AMI-trap/on_device_classifier] Create classifier for Costa Rica moths (Issue #28) CAUTION: This email originated from outside of the organisation. Do not click links or open attachments unless you recognise the sender and know the content is safe. By the way, @JennaLawson<https://github.com/JennaLawson> GBIF has this neat online tool you can use to check for species in the GBIF backbone: https://www.gbif.org/tools/species-lookup Our code (adapted from Rolnick) just uses the API version of this. But if you yourself would like to dynamically check any given species checklist, that page is quite useful. It will highlight missing species, and even give you multiple alternative match options for species that couldn't be matched. Its quite good for exploration. — Reply to this email directly, view it on GitHub<#28 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AY7MMXKQ7KNPWOAJDY5CZILYA7QGDAVCNFSM6AAAAAA5F57LTWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTONZXGUZTSMBZGQ>. You are receiving this because you were mentioned.Message ID: ***@***.***> This email and any attachments are intended solely for the named recipients and are confidential. If you are not the intended recipient, please reply to the email to highlight the error and delete this email from your system; you must not use, disclose, copy, or distribute this email or any of its attachments. UK Centre for Ecology & Hydrology (UKCEH) has taken reasonable precautions to minimise risk of this email or any attachments containing viruses or malware, but the recipient should carry out its own virus and malware checks before opening the attachments. UKCEH does not accept any liability for any losses or damages which the recipient may sustain due to presence of any viruses. Opinions, conclusions or other information in this message and attachments that are not related directly to UKCEH business are solely those of the author and do not represent the views of UKCEH. We process your personal data in accordance with our Privacy Notice, available on the UKCEH website. https://www.ceh.ac.uk/privacy-notice Registered office address; Maclean Building Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire, United Kingdom, OX10 8BB Companies Registered Name; UK Centre for Ecology & Hydrology Place of Registration; England Registered Company Number; 11314957

[LevanBokeria]

Downloading of images is paused until a potential taxonomic inconsistency is resolved for some of the species. See issue

[LevanBokeria]

@JennaLawson I forgot to mention, that when checking the species in the google sheet list, please also check for match_type = HIGHERRANK. There are 3 such rows, which indicate that the exact match was not found on GBIF, and the API returned a GENUS match instead.

[JennaLawson]

@LevanBokeria apologies but the list sent before had some butterflies in it. I have removed the butterfly families and am attaching here a list with just moth species.
Moths of Costa Rica_wo_butterflies .csv

[KatrionaGoldmann]

Completed in costarica_model.sh . Closing issue.

[mihow]

Thanks @KatrionaGoldmann, do you have a version of this CSV with a column for the GBIF key that you matched do? The GBIF key you used to fetch training images for each species.