Since I was a child in Brazil, I've been fascinated by bees, and I still dream, like a sort of modern Sherlock Holmes, of becoming a beekeeper when I retire. My retirement dream is to be a small-time beekeeper with a selected number of colonies of bees, rearing quality queens that can survive in our harsh environment while introducing the traits I would like to see in them on a pretty small scale. Over the last few years, I've been in contact with some passionate beekeepers, some that want to do it for a hobby, and some that want to do it for the experience for a long time; I've been exploring many hypotheses of applying technology, in particular, AI to enhance and protect beekeeping, helping them to survive our tough metropolitan environments. Fortunately, there has been a growing awareness about our pollinators and the risk they face from the pressures of human activity. In response, many researchers, farmers, and citizens are coming together to help protect these essential insects and their habitats.

This week, craft beer company Bira landed new funding to expand its geographic reach while Torr FoodTech grabbed $12 million for its unusual and tech-centric approach to snack bars. In agtech, Clarifruit also raised $12 million while more layoffs struck the food delivery sector. Craft beer maker Bira 91 lands $70 million round led by beer company Kirin. Bira will use the funding to build more breweries and expand geographical reach of the Bira line of beverages. Sustainable grocery startup Modern Milkman raises £50 million ($60 million) after Series C close.

Pests destroy up to 40% of the world's crops each year, causing $220 billion in economic losses, according to the UN Food and Agriculture Organization (FAO). Trapview is harnessing the power of AI to help tackle the problem. The Slovenian company has developed a device that traps and identifies pests, and acts as an advance warning system by predicting how they will spread. "We've built the biggest database of pictures of insects in the world, which allows us to really use modern AI-based computing vision in the most optimal way," says Matej Štefančič, CEO of Trapview and parent company EFOS. As climate change causes species to spread, and disrupts the migration patterns of highly destructive pests, such as desert locusts, Štefančič hopes to help farmers save their crops with quicker, smarter interventions.

Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and achieve efficiency by upskilling and scaling citizen developers. In 2010, three psychologists from the University of British Columbia published a paper with an intriguing title: The WEIRDest people in the world? Paradoxically, the paper was about Americans. The three scientists had devoted their research careers to cross-cultural variability of human psychology and traveled the seven seas to study small-scale tribal societies. In the paper, they voiced a growing concern about how heavily the humanities -- psychology, economics, sociology, political science and others -- were relying on samples of Americans.

Combining multi-spectral satellite data and machine learning has been suggested as a method for monitoring plastic pollutants in the ocean environment. Recent studies have made theoretical progress regarding the identification of marine plastic via machine learning. However, no study has assessed the application of these methods for mapping and monitoring marine-plastic density. As such, this paper comprised of three main components: (1) the development of a machine learning model, (2) the construction of the MAP-Mapper, an automated tool for mapping marine-plastic density, and finally (3) an evaluation of the whole system for out-of-distribution test locations. The findings from this paper leverage the fact that machine learning models need to be high-precision to reduce the impact of false positives on results. The developed MAP-Mapper architectures provide users choices to reach high-precision ($\textit{abbv.}$ -HP) or optimum precision-recall ($\textit{abbv.}$ -Opt) values in terms of the training/test data set. Our MAP-Mapper-HP model greatly increased the precision of plastic detection to 95\%, whilst MAP-Mapper-Opt reaches precision-recall pair of 87\%-88\%. The MAP-Mapper contributes to the literature with the first tool to exploit advanced deep/machine learning and multi-spectral imagery to map marine-plastic density in automated software. The proposed data pipeline has taken a novel approach to map plastic density in ocean regions. As such, this enables an initial assessment of the challenges and opportunities of this method to help guide future work and scientific study.

In astronomical surveys, such as the Zwicky Transient Facility, supernovae (SNe) are relatively uncommon objects compared to other classes of variable events. Along with this scarcity, the processing of multi-band light-curves is a challenging task due to the highly irregular cadence, long time gaps, missing-values, few observations, etc. These issues are particularly detrimental to the analysis of transient events: SN-like light-curves. We offer three main contributions: 1) Based on temporal modulation and attention mechanisms, we propose a Deep attention model (TimeModAttn) to classify multi-band light-curves of different SN types, avoiding photometric or hand-crafted feature computations, missing-value assumptions, and explicit imputation/interpolation methods. 2) We propose a model for the synthetic generation of SN multi-band light-curves based on the Supernova Parametric Model, allowing us to increase the number of samples and the diversity of cadence. Thus, the TimeModAttn model is first pre-trained using synthetic light-curves. Then, a fine-tuning process is performed. The TimeModAttn model outperformed other Deep Learning models, based on Recurrent Neural Networks, in two scenarios: late-classification and early-classification. Also, the TimeModAttn model outperformed a Balanced Random Forest (BRF) classifier (trained with real data), increasing the balanced-$F_1$score from $\approx.525$ to $\approx.596$. When training the BRF with synthetic data, this model achieved similar performance to the TimeModAttn model proposed while still maintaining extra advantages. 3) We conducted interpretability experiments. High attention scores were obtained for observations earlier than and close to the SN brightness peaks. This also correlated with an early highly variability of the learned temporal modulation.

There has been increasing attention on planning model learning in classical planning. Most existing approaches, however, focus on learning planning models from structured data in symbolic representations. It is often difficult to obtain such structured data in real-world scenarios. Although a number of approaches have been developed for learning planning models from fully observed unstructured data (e.g., images), in many scenarios raw observations are often incomplete. In this paper, we provide a novel framework, \aType{Recplan}, for learning a transition model from partially observed raw image traces. More specifically, by considering the preceding and subsequent images in a trace, we learn the latent state representations of raw observations and then build a transition model based on such representations. Additionally, we propose a neural-network-based approach to learn a heuristic model that estimates the distance toward a given goal observation. Based on the learned transition model and heuristic model, we implement a classical planner for images. We exhibit empirically that our approach is more effective than a state-of-the-art approach of learning visual planning models in the environment with incomplete observations.

Multilingual models are often particularly dependent on scaling to generalize to a growing number of languages. Compression techniques are widely relied upon to reconcile the growth in model size with real world resource constraints, but compression can have a disparate effect on model performance for low-resource languages. It is thus crucial to understand the trade-offs between scale, multilingualism, and compression. In this work, we propose an experimental framework to characterize the impact of sparsifying multilingual pre-trained language models during fine-tuning. Applying this framework to mBERT named entity recognition models across 40 languages, we find that compression confers several intriguing and previously unknown generalization properties. In contrast to prior findings, we find that compression may improve model robustness over dense models. We additionally observe that under certain sparsification regimes compression may aid, rather than disproportionately impact the performance of low-resource languages.

Using code-mixed data in natural language processing (NLP) research currently gets a lot of attention. Language identification of social media code-mixed text has been an interesting problem of study in recent years due to the advancement and influences of social media in communication. This paper presents the Instituto Polit\'ecnico Nacional, Centro de Investigaci\'on en Computaci\'on (CIC) team's system description paper for the CoLI-Kanglish shared task at ICON2022. In this paper, we propose the use of a Transformer based model for word-level language identification in code-mixed Kannada English texts. The proposed model on the CoLI-Kenglish dataset achieves a weighted F1-score of 0.84 and a macro F1-score of 0.61.

During the outbreak of COVID-19 pandemic, several research areas joined efforts to mitigate the damages caused by SARS-CoV-2. In this paper we present an interpretability analysis of a convolutional neural network based model for COVID-19 detection in audios. We investigate which features are important for model decision process, investigating spectrograms, F0, F0 standard deviation, sex and age. Following, we analyse model decisions by generating heat maps for the trained models to capture their attention during the decision process. Focusing on a explainable Inteligence Artificial approach, we show that studied models can taken unbiased decisions even in the presence of spurious data in the training set, given the adequate preprocessing steps. Our best model has 94.44% of accuracy in detection, with results indicating that models favors spectrograms for the decision process, particularly, high energy areas in the spectrogram related to prosodic domains, while F0 also leads to efficient COVID-19 detection.