Come with us as we take a ride into Painted Cave: California’s largest sea cave – and the FOURTH largest in the world! See the beautiful rainbow colors on the walls and learn some fun facts about the cave and the birds you can hear (sound on)!

This short video is dedicated to all our subs as a special thank you for helping us reach over 700 subs now!

Or watch it on our YouTube channel here and explore more of our nature content! Learn more about our videographer Hannah here!

The post Painted Cave in Channel Islands! appeared first on The Curio Cat.

This winter, it was all about the hoar frost and the hair ice. The hair ice captured our eyes for sure – but if you’re anything like us, hearing the word “hoar” got your attention too!

Check out our video to learn the difference in these two types of winter phenomena as well as a third one – rime ice – and to see some awesome up close footage of these beautiful and somewhat rare natural wonders!

Or watch it on our YouTube channel here. To learn more about our videographer Hannah, click here!

The post Hoar Frost VS Hair Ice! appeared first on The Curio Cat.

The night sky world has been abuzz with talk of the great Planet Parade of 2025! January skies brought us FIVE bright planets: Saturn, Venus, Mars, Jupiter, Neptune, and Uranus! And into February the skies will add one more to the list – Mercury!

We had some clear skies in late January and were able to capture distant Uranus, Jupiter and even two of Jupiter’s moons: Europa and Ganymede! Sky and Telescope has an excellent tool for locating and identifying Jupiter and its moon given the time and date – check it out here!

Ganymede is largest moon in our solar system and the only one with its own magnetic field. Europa is the moon often depicted as our second home in many sci-fi movies – that’s because there’s evidence showing it has a large saltwater ocean and just might be our best bet to support life outside of Earth.

You can see most of these visible planets, including Jupiter, with the naked eye. But to see Uranus and Neptune, as well as Jupiter’s moons, you’ll need some strong binoculars or a telescope. We were able to capture our images with our Canon 100-500mm telephoto lens. While our photos aren’t high def or detailed, it was no less thrilling to be able to see our solar system’s largest planet and some of its moons.

Due to our location, we weren’t able to get Saturn – but you may still be able to just after sunset. Here’s a throwback to when we did capture Saturn back in 2023 with that same Canon lens. You can even see the rings! So exciting!

Did you see or capture any of the planets or other celestial bodies during the great planet parade? We’d love to see your photos! Tag us on socials and tell us how you were able to capture these distant neighbors!

The post Planet Parade 2025! appeared first on The Curio Cat.

I spent a couple of days scouring the park for the best views to the West, holding up my phone to align the sun with the planner in my PhotoPills app and framing some potential compositions. I’m sure hikers thought I was desperately searching for a cell signal.

The first night, I settled next to a small pullout on the side of the road near the Arch Rock trail. The wide open expanses with minimal obstructions seemed the most promising for guaranteed comet sightings. The sunset was magnificent but seemed to drag on for eternity.

Then, after about 30 minutes, a ghostly white tail emerged, and I gasped in bewilderment! Finally, after 80,000 years, I got my first glimpse of comet Tsuchinshan–ATLAS! This icy solar body flies towards us from the cosmographic boundaries of our home system in the Oort cloud. It’s a leftover from the formation of our solar system, as all comets are believed to be, and it was finally in my field of view.

This particular night, October 12, was the comet’s closest approach to us Earthlings – a mere 44 million miles away. Sadly, this “long-period comet” didn’t linger very long. After about 20 or 30 minutes, it vanished behind the distant mountains on the horizon.

The next morning, I discovered an even more dramatic comet-viewing point – the base of Ryan Mountain. There I found a field of tall old growth Joshua Trees, with their spiny fingers curling up towards the stars. This would surely make for some striking foreground subjects in my comet photos. I returned about an hour before sunset to scout my ideal viewing spot, set up my gear, and practice framing some shots.

I didn’t mind the wait. Desert sunsets are glorious transformations. As the sun falls, the fiery hues of the day give way to the deep violets of the night. The fury of the burning air shifts to gentle cool breezes and the desert’s nocturnal inhabitants begin to emerge. The pressing silence of the stifling daytime temperatures is interrupted by the fluttering of bat wings here and there which gives way to occasional sounds of scurrying in the sand by the bunnies and various desert rodents and reptiles.

Venus is the first to greet me as we descend into darkness, a bright beacon to my left. Next, the bright orange star Arcturus begins to glimmer faintly to my right and I have my markers! I shift my focus to a small area between them, where I expect the comet to appear. And I wait with even greater anticipation than I did the night before.

Tsuchinshan–ATLAS appeared much higher in the sky this time – almost exactly halfway between Venus and Arcturus.

Its tail seemed to grow longer and the comet was more generous with its time on this second night – giving me the opportunity to explore my creativity AND work on getting some closeup shots!

This carbon depleted, cyanide emitting behemoth has a head or “coma” about 130,000 miles in diameter, with a tail reaching out about 18 MILLION miles! Just what causes the tail you ask?? Well, as the giant ball of ice passes by the sun, it gets roasted and baked. This causes gasses to blast off of the comet, dragging dust particles behind it and giving us quite a show!

After about 45 minutes, my time with Tsuchinshan–ATLAS began to wind down as it slipped closer and closer towards the mountainous horizon. I put away my camera and admired the comet while I pondered what those archaic homo sapiens thought when they saw Tsuchinshan–ATLAS blazing through the sky. What were their lives like, what worries did they ruminate over while staring up at the cosmos? Did they ever stop to look up that long? Did they even delve into philosophical issues such as the meaning of life like me and so many others?

I stood in this vast ancient desert, staring up into the sky with awe, as a member of that distant species – ancestor to us all – possibly did some 80,000 years ago and felt connected to them and to this timeless landscape. The comet has not only bridged space, but the centuries as well.

The post Comet of the Century – CAPTURED! appeared first on The Curio Cat.

As a fun exercise, the CurioCat team competed in our first ever IEEE BigData Cup Challenge, entitled “Building Extraction”. The premise of this competition was to design a neural network to extract building footprints. Specifically, given a satellite image, the neural network must do three things: (a) detect individual buildings, (b) fit each building’s footprint to a polygon, and (c) list the vertices of every polygon. Below is a preview of a test image and our answer. Looks good so far!

What is Instance Segmentation?

In Computer Vision (CV), this task is known as instance segmentation. “Instance” indicates that each building is to be segmented individually. Semantic segmentation, on the other hand, treats objects of the same class as one entity, meaning that a cluster of buildings is segmented as a giant blob.

The best way to understand the task is to look at the training data. Our training data consisted of 9000 image pairs. The input is a satellite image and the output is the corresponding mask of building footprints. Below, we show an example of one image pair. On the right is satellite image of a Chicago neighborhood. On the left is the mask showing three classes: background (purple), building interior (green), and building outline (yellow). Eagle-eyed readers will note that the mask has some noticeable errors! This is because a human had to segment this image by hand!

Creating a Neural Network for Image Mapping

So, our task boils down to creating a neural network that can “map” the input image to the output image. This task is challenging because the test images consists of buildings in a variety of settings: (1) rural, (2) suburban, (3) urban, (4) commercial, (5) cityscape, (6) industrial, and (7) seaport. To be effective, a neural network must “generalize” well over all potential settings.

To do this, we created a neural network using a Resnet50 backbone. Resnet50 is a type of U-net architecture that is specifically designed for mapping image pairs. After our neural network predicts the output mask, we can easily detect and extract building footprints using the Python function cv2.findContours. Below are some more of our test results for different settings:

Why Did Our AI Hit a Ceiling??

So, how did our neural network perform overall? Our neural network was excellent in rural, suburban, and urban settings. However, our neural network was relatively weak in commercial, cityscape, industrial, and seaport areas. Why is this the case? Where did we go wrong?

Luckily, the answer is simple. Remember, a neural network can only go as far as its training data allows! So, if you want your neural network to learn seaports, you need to show it many seaports. Alas, due to time constraints, the training set we built was limited to certain types of areas. Specifically, we trained our neural network on the INRIA dataset for Tyrol Austria, Kitsap WA, and Chicago IL, which consists almost exclusively of rural, suburban, and urban areas. Therefore, it makes sense that our neural network would outperform in these areas.

Lessons Learned:

If we could do this BigData competition over, here is what we would change:

• We would have added more commercial, city, industrial, and seaport areas into our training set.
• We would have trained our neural network for more than 3 epochs. Research suggests 10-100 epochs.
• Our neural network was fooled by objects that look like buildings, including shipping containers, satellite dishes, grain silos, storage tanks, swimming pools, large air conditioning units, and even tennis courts. With this knowledge, we would have added images of these objects to inform our neural network of what not to segment.
• Our neural network was fooled by shadows. In images where the sun was low, peaked rooftops possessed different shades: the side facing toward the sun and the side facing away from the sun were lighter and darker, respectively. Instead of segmenting the building as one building, the neural network mistakenly “saw” two buildings. So, our training set should have included satellite images from different times of day.
• Our training dataset consisted of moderate resolution images. However, the testing set contained some grainy images. To strengthen our neural network’s ability to generalize, we could have injected Gaussian noise into our training set.
• Our training images were more zoomed-in than our testing images. So interpolating down our training images may have been helpful.
• For our multiclass classification, we gave our three classes, i.e., background, interior, and outline, weights of 0.25, 0.25, and 0.50, respectively. However, given that there are far fewer outline pixels, perhaps we should have given the outline an even greater weight.
• We would have experimented with different backbones. Instead of Resnet50, we could have tried DeepLab, Mask R-CNN, or YOLO.
• Finally, we could have tried a new technology like vision transformers.

The post IEEE BigData Cup Challenge – Lessons Learned! appeared first on The Curio Cat.

Happy World Photography Day! We’ve had a summer FULL of orb weavers here at The Curio Cat headquarters in Los Angeles County, much to the delight of our resident photographer Hannah because she loves to play with her new macro lens!

We measured these tiny little arachnids at less than 3mm – see the white spot in the pic below? That’s the spider in our first picture below – just to give you a sense of how miniscule that is – and how powerful those dedicated macro lenses can be!

This was by far one of the tiniest spiders our photographer has been able to capture. Orb weavers are known for their spiral wheel-shaped webs, and what a beautiful web this miniature one created!

And he’s not alone! He has two very hungry neighbors that Hannah managed to capture mid-meal!

Orb weavers are one of the largest families of spiders in the world. They’re super beneficial to your gardens as they eat TWICE their weight in insects each day, keeping your gardens free from pests! So if you see them, let them be!

Check our our short on YouTube here!

The post Orb Weavers – World Photography Day 2024! appeared first on The Curio Cat.

Come with us as we take you up over 8400 feet elevation and through a magnificent alpine wonderland on this incredible Utah hiking trail – as a thank you for reaching 600+ subscribers on YouTube!

For our thank you videos, we like to break from our normal content style. So we hope you enjoy this Utah hiking trail asmr. All the sounds you hear – from the abundant birdsongs and wind shaking the aspen leaves to all the waterfalls – was recorded on the trail as we hiked. So it’s real-time, blissful, peaceful immersion! That being said, please excuse the few moments where you can hear our videographer breathing – the trails are real butt-burners with lots of elevation gain LOL!!

The prominent birdsong you’ll hear is the Warbling Vireo and a little MacGillivray’s Warbler except where otherwise noted in the video itself. (Spoiler alert: we got some great audio of the very elusive Hermit Thrush!) And be sure to keep an ear out for all the croaking frogs!

This area ended up being one of our ultimate favorite hiking destinations of all time! Let us know your favorite trails in the YouTube comments. Maybe we’ll feature it in our next thank you video (and give you a shout out of course)!

We truly are so grateful for everyone’s support of our little channel! Thank you so much for subscribing and we look forward to sharing more nature content and student conferences with you as we go along!

Or watch it on our YouTube channel here. To learn more about our videographer, Hannah, click here!

The post A Utah Hiking Trail Experience! appeared first on The Curio Cat.

Birding’s biggest day was May 11, 2024 and we had a special treat for everyone! We revealed a brand new birding hotspot! We were the first birding team to EVER bird at this location on a Global Big Day! Our team was lucky enough to do our bird count at California’s newest nature preserve and had the place to ourselves all morning!

We saw all of our target species and tons of others as well. This spot truly is a vital and vibrant stop for these migratory birds making their journey along the Pacific Flyway. Check out our videos below to get a glimpse of California’s latest wild space as well as our stats and favorite pics from the day!

So just in case you don’t follow along on all our socials – here’s our reveal video:

And if you’re curious about our stats and highlights from the Global Big Day count, here’s our results video that includes a look at the new preserve and some of our favorite bird photos of the day!

Or check out the videos on our YouTube channel here! To learn more about our lead birder, photographer, and videographer Hannah, click here!

The post Birding Hotspot – REVEALED!! appeared first on The Curio Cat.

Tomorrow is birding’s biggest day – Global Big Day – and we’ve got a big surprise for you: a new location for a birding hotspot that’s NEVER been birded before on a Global Big Day!

Here’s a little sneak peak…can you guess where this new hotspot is? Let us know what you think in the comments and be sure to subscribe to our YouTube channel and stay tuned to find out where we’ll be on tomorrow’s big birding adventure!

This year’s Global Big Day theme is insects and how important they are to birds. Join our birding team – The CurioCat Conservation Team – and bird with us virtually, even from your own backyard for a chance to be the top birding team of the day! Email hannah@thecuriocat.com for details. (more about our birding guru and media manager Hannah here!)

Here’s some helpful links if you’d like to learn more about Global Big Day (which is also World Migratory Bird Day) and other ways to participate!

https://ebird.org/news/global-big-day-2024

https://www.migratorybirdday.org

The post New Birding Hotspot Reveal! appeared first on The Curio Cat.

We were so excited to witness SpaceX’s latest rocket launch/flight over the Southern California desert last week! It just so happens that we’ve been building some AI rocket simulations for an upcoming student research project studying the effects of aerodynamics and various rocket designs.

Check out a little demonstration of some of our rocket A.I. sims as well as some awesome 4K footage of the SpaceX rocket flying over the desert!

Or watch it on our YouTube channel here. To learn more about our AI sim guru, Derek, click here!

The post AI Rocket Simulations appeared first on The Curio Cat.