A huge thank you to everyone who took part in the GeoAI Aquaculture Pond Identification Challenge.Looking across the top solutions, a few strong themes emerged:... See more

Can we get information on the winning submission(s)?!

is there anyone who is having problem with selecting final two submissions or is it just me?@meganomaly It says "There was an issue saving your selections" and... See more

@meganomaly can we use test set missingness patterns/ statistics to derive training model inputs?

@AJoel, & @meganomaly I'd like to flag a pattern I noticed on the leaderboard for Zindi Team to verify. I'm not accusing anyone — just presenting what's pub... See more

"Hello, I have a question: does 'month 01' in the training dataset correspond to the same month in the year of the test dataset? (For instance, if month 01 repr... See more

According to the rules, the external data is not allowed, but could we use the models with satellite pre-training for feature extraction?Update: I found the "Yo... See more

Hi, could the organizers please clarify the rule about probability thresholds?The competition page says that setting a probability threshold is strictly forbidd... See more

After a considerable amount of submissions, I have realized the 90s club are indeed doing impressive work.For me, no CV LB correlation in this competition whats... See more

Is model ensembling / averaging allowed? I am stuck at 0.8 no matter how i engineer my features (using CatBoost model). I want to introduce some model ensemb... See more

I'm currently on my own team. It says I can only have 5 submissions per day and 100 total submissions. But the competition overview states a limit of 10 submiss... See more

Hi all,Based on the latest information, we should expect all entries to have 4,5, or 6 continuous months with valid data. For the other months, all values shoul... See more

Hi I just joined, wanted some clarity on what data we are allowed to use. The compeition rules say this:Only freely accessible satellite data may be usedYou may... See more

Hi everyone, Thank you for your patience, and thank you to those who raised concerns about the original challenge data. We have reviewed the issue carefully wi... See more

I want to raise a broader concern about the state of recent Zindi competitions.This year, several competitions have had serious leakage issues. In some cases, t... See more

Everyone are getting 1.0 score is this real model or?

Hi everyone,I'm just getting started and I'm not sure where to begin. I have a couple of beginner questions: What image size should I use or download for the be... See more

i dont understand this for each target... arent these single value overall model metrics?

@AJoel and @meganomaly, Please assist with the above mentioned issue, so far about 19 people have the perfect score and @BigZ already exposed the exploit.Thank... See more

The rules state a maximum of 1,000 training samples per pilot region including self-collected samples, but the Full Rules also say to use only the provided data... See more

LOL 😂The competition ended so fast.Top 4 contestants: 1.000000000 Me: Still reading the dataset description 😭💀UPDATE: There is a leak🙂

I would like to raise a critical issue regarding the dataset structure of the challenge that allows anyone to achieve a perfect score of 1.0 on the leaderboard... See more

Hi everyone! I'm stuck around 0.953 on the leaderboard and can't seem to get past it, while many of you are at 0.98+. I'd really appreciate any general guidance... See more