Well, you’ve done it again. Notes from Nature 2.0 just reached 1 MILLION, so let’s celebrate. It took about 994 days, which is around 1,000 classifications/transcriptions a day. We’ve had so many wonderful milestones along the way such as online and onsite events, transcription challenges and lots of lots of engaging research questions. Not to mention the many wonderful interactions with our amazing volunteers. We could never have imagined the community that would coalesced around this project. It would literally be nothing without all of you!
You can even review the over 175 expeditions that we have completed since starting Notes from Nature 2.0. We transitioned from Notes from Nature 1.0 with about 1,011,400 transcriptions, so this puts us well over 2 million for the entire project!
As always the site has lots of content to engage with and always plenty of herbarium specimens to transcribe. We have been particularly excited about our Labs, which currently feature 3 different phenology projects.
The Notes from Nature Team
As some have already noticed we are very close to a very big milestone! We are about 2,000 classification away from reaching 1 MILLION on Notes from Nature 2.0. Yes, we have reached 1 million before, but we are even more thrilled this time around.
There is so much great activity on Notes from Nature and we continue to plan for an exciting future. We have 20+ expeditions with a wide variety of content at the site right now. There are a number of school projects going on as well as specific research question being addressed. On top of all that we engage with potential new collaborators on a daily basis!
With all that said, the question on our minds right now is who will make the 1 million classification? Please consider spending a few extra minutes on the site the next few days to help us celebrate all of the wonderful effort. And maybe you will be the one to take that 1 millionth classification!
— The Notes from Nature Team
Artificial intelligence. Machine learning. I’m sure you’ve heard these buzzwords; they’re all the rage in technology lately. As it turns out, they are all the rage in biodiversity informatics too. The newest Notes from Nature expedition for plant specimens from the genus Prunus – which includes many plants you’re familiar with like cherries, almonds, and peaches – is part of a larger project on machine learning led by scientists at the Florida Museum of Natural History. Over the past year, we have scored thousands of images of digitized herbarium specimens from the genera Prunus and Acer for different character states – the presence of fruits, flowers, and unfolded leaves. We used these manually scored images to train and test a machine learning algorithm to see how well it is able to identify these characters on its own.
To get a better idea of whether or not our machine learning algorithm performs better than a human given the task of scoring these images, we recruited volunteers to score images of Prunus and Acer herbarium specimens using our criteria. On average, the volunteers were able to properly identify flowers, fruits, and unfolded leaves more than 95% of the time. That is pretty good! This led us to wonder if scoring by citizen scientists could create a training set comparable to the training set we made by spending hours poring over thousands of specimen images.
If this effort proves to be a success, crowdsourcing could be a great way to coordinate efforts to expand the possibilities of machine learning to new groups of plants! This could expand datasets about plant phenology – the study of the timing of life cycle changes in plants – at a more rapid pace than is possible right now. The phenology of plants is known to be closely linked to environmental conditions that plants experience. As the Earth’s climate changes in new ways, the impact of these changes may affect species of plants differently, depending on the areas where they are found and the different characteristics of the species. In order to fully understand the changes plant phenology is undergoing due to current climate change, though, we need a stronger understanding of plant phenology in the past. Herbarium specimens inherently carry phenological information, but it is not easily accessible in a usable format for researchers. Help us learn more about plant phenology and machine learning methods by participating in this Prunus phenology expedition!
For Notes From Nature volunteers who have participated in plant phenology expeditions in the past, it is important to note that our criteria for scoring the presence of flowers, fruits, or unfolded leaves may differ from previous expeditions. We encourage all volunteers for this expedition to view the help materials for these scorings by clicking the “need more help with this task?” link on the scoring page. This will undoubtedly help you make more accurate decisions! Also, you may come across some specimens where it is very hard to tell whether a specific trait is present or absent. Don’t stress, and just make your best possible guess! Happy scoring!
Happy holidays from everyone at Notes from Nature and a huge thanks for an amazing year. So far, and the year isn’t quite done yet, we’ve totaled 430,423 classifications. Considering we are this close to 900,000 classifications, that is even more incredible. Nearly half our classifications came just this year!
For many of our devoted transcribers and classifiers, this may come as no surprise. We have tried hard to make some tasks more simple and discrete, and this has really made things faster and hopefully also helped get more people involved. We also launched a whopping 87 expeditions this year, and had 68 (so far) finish in 2018.
So here is a question. When do we hit a million classifications? We hope soon! Current rates suggest sometime in mid to late March, but can we lower that timeline? Our best month so far in 2018 was November, with 53,019 classifications. What are the chances we could hit a million by end of February? Ambitious? We think it could happen and we’ll be pushing hard ourselves to keep getting up interesting content and new expeditions. We’ll also be announcing some great new features and improvements that we hope makes Notes from Nature that much easier, better and interesting. More on that very soon!
Happy Holidays from everyone at NFN and thanks for taking notes from nature.
A holiday-themed specimen above from the University of Florida Herbarium. Frankincense comes from the genus Boswellia and especially Boswellia sacra (shown above).The resin of the tree is what is harvested, and used as incense. It has been used in religious ceremonies for millennia and was one of the gifts brought by the Three Wise Men. Over-harvesting and conversion of frankincense woods to agriculture are threats to the long-term persistence of Boswellia.
Northwest Arkansas is now recognized as the 14th fastest growing metropolitan area in the United States. The population of the region doubled between 1990 and 2010 and is now adding more than 1,000 people per month. Most of this growth has occurred in Benton and Washington counties. As a result of this rapid growth, there is unprecedented interest in incorporating conservation-related information as the region plans for future growth.
It is already known that Benton and Washington counties are among the most biologically diverse in the state, but no comprehensive inventory has been conducted for either county. The Arkansas Natural Heritage Commission (ANHC) is embarking on this inventory now, with the ultimate goal of identifying the highest priority areas and/or habitats for conservation. The first step in this process is to gather all available information on what lives where. A treasure trove of herbarium specimens exists from these counties but very little of the label data have been digitized. That’s where you can help the scientists of the ANHC as they explore the biological diversity of Northwest Arkansas.
Please try out the two new Plants of Northwest Arkansas expeditions.
There are almost 500 non-native plants that now call Tennessee home. These plants threaten native Tennessee ecosystems. Detection and monitoring, of these species present tremendous challenges to conservation groups. As a first line of defense, organizations such as the Tennessee Invasive Plant Council (TN-IPC) work to list and rank non-native species. Up until recently, organizations such as these have relied heavily on expert opinion and experience to rank non-native species. However, with the onset of metadata technology, the ability to access large amounts of information has transformed the ways in which we might enhance our understanding of the threat non-native species pose across the landscape.
This expedition will assist University of Tennessee at Chattanooga graduate student Courtney Alley in collecting data for her thesis research that will utilize this advancement in technology to further our understanding of non-native plant species. Ultimately, this information will be used to map the locations of these invasive plant species and eventually determine a pattern of spread throughout the state. With your help, we can use these data to develop more effective detection and monitoring techniques for non-native plants!
I would like to thank all the citizen scientists who have worked to complete these expeditions! Even though this is the fourth Tennessee Invaders we have almost 300 species left until we have transcribed all the herbarium specimens for non-native plants in Tennessee! Keep up the hard work!
The Notes from Nature team has been thinking a lot about how to take some bold next steps to make transcription faster and better. To that end, we have launched something of an outlier expedition. This new expedition, which we have called “Label Babel” asks for help delineating the main label on herbarium sheets, which is usually – but not always! – in the bottom right corner. We also are asking you to tell us if the label is “all typewritten”, “all handwritten” or “both handwritten and typewritten”.
So you might be thinking “Why is Notes from Nature asking you to do this?” The short answer is that we think we can use machine learning approaches to detect where a label is, and the type of content (handwritten, typewritten, both) on the label. Your work helps us develop a training dataset for this machine learning effort. If we can indeed build this machine learning approach, it would allow us to have a quick way to sort different herbarium sheets and use the right Optical Character Recognition or Handwriting Detection Tools depending on the label.
We hope this is a fun diversion from the usual task and that the work you are doing here can help us build a better Notes from Nature. We will let you know how we do building the machine learning tools from the initial efforts here as soon as we can.
— The Notes from Nature Team