Canada

Accurate crop type maps are an essential source of information for monitoring yield progress at scale, projecting global crop production, and planning effective policies. To date, however, crop type maps remain challenging to create in low- and middle-income countries due to a lack of ground truth labels for training machine learning models. Field surveys are the gold standard in terms of accuracy but require an often-prohibitively large amount of time, money, and statistical capacity. 
In recent years, street-level imagery, such as Google Street View, KartaView, and Mapillary, has become available around the world. Such imagery contains rich information about crop types grown at particular locations and times. 
In this work, we develop an automated system to generate crop type ground references using deep learning and Google Street View imagery. The method efficiently curates a set of street-view images containing crop fields, trains a model to predict crop types using either weakly-labeled images from disparate out-of-domain sources or zero-shot labeled street view images with GPT-4V, and combines the predicted labels with remote sensing time series to create a wall-to-wall crop type map. We show that, in Thailand, the resulting country-wide map of rice, cassava, maize, and sugarcane achieves an accuracy of 93%. As the availability of roadside imagery expands, our pipeline provides a way to map crop types at scale around the globe, especially in underserved smallholder regions.

AAAI 2024

Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types

ml: time-series/data streams

ml: transfer

cv: applications

domain adaptation

multi-task learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Large language models (LLMs) have demonstrated impressive proficiency in information retrieval, while they are prone to generating incorrect responses that conflict with reality, a phenomenon known as intrinsic hallucination. The critical challenge lies in the unclear and unreliable fact distribution within LLMs trained on vast amounts of data. The prevalent approach frames the factual detection task as a question-answering paradigm, where the LLMs are asked about factual knowledge and examined for correctness. However, existing studies primarily focused on deriving test cases only from several specific domains, such as movies and sports, limiting the comprehensive observation of missing knowledge and the analysis of unexpected hallucinations. To address this issue, we propose OntoFact, an adaptive framework for detecting unknown facts of LLMs, devoted to mining the ontology-level skeleton of the missing knowledge. Specifically, we argue that LLMs could expose the ontology-based similarity among missing facts and introduce five representative knowledge graphs (KGs) as benchmarks. We further devise a sophisticated ontology-driven reinforcement learning (ORL) mechanism to produce error-prone test cases with specific entities and relations automatically. The ORL mechanism rewards the KGs for navigating toward a feasible direction for unveiling factual errors. Moreover, empirical efforts demonstrate that dominant LLMs are biased towards answering Yes rather than No, regardless of whether this knowledge is included. To mitigate the overconfidence of LLMs, we leverage a hallucination-free detection (HFD) strategy to tackle unfair comparisons between baselines, thereby boosting the result robustness. Experimental results on 5 datasets, using 32 representative LLMs, reveal a general lack of fact in current LLMs. Notably, ChatGPT exhibits fact error rates of 51.6% on DBpedia and 64.7% on YAGO, respectively. Additionally, the ORL mechanism demonstrates promising error prediction scores, with F1 scores ranging from 70% to 90% across most LLMs. Compared to the exhaustive testing, ORL achieves an average recall of 80% while reducing evaluation time by 35.29% to 63.12%.

OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning

In recent years, the rapid advancement of artificial intelligence (AI) has fostered an urgent need to better prepare current and future educators to be able to integrate AI technologies in their teaching and to teach AI literacy to PreK-12 students. While many organizations have developed professional learning opportunities for inservice educators, a gap remains for resources specifically designed for those facilitating and enrolled in Educator Preparation Programs (EPPs). In response to this gap, the International Society for Technology in Education (ISTE) launched its first AI Explorations for EPPs Faculty Fellowship. As a result of the Faculty Fellows’ collaboration, this paper articulates a framework of seven critical strategies with the potential to address the urgent need EPPs have in preparing preservice teachers to effectively integrate AI-powered instructional tools and to teach this new area of content knowledge in PreK-12 classrooms. In addition, we provide a review of literature and an overview of the emerging needs for integrating AI education in EPPs. We demonstrate why support for preservice teachers’ critical examination and application of AI, including a focus on the issues of equity, ethics, and culturally responsive teaching, is essential to their later success in PreK-12 classrooms. Recommendations for further research and learning are also provided to promote community-wide initiatives for supporting the integration of AI in education through Educator Preparation Programs and beyond.

A Framework for Approaching AI Education in Educator Preparation Programs | VIDEO

High school teachers from many disciplines have growing interests in teaching about artificial intelligence (AI). This cross-disciplinary interest reflects the prevalence of AI tools across society, such as Generative AI tools built upon Large Language Models (LLM). However, high school classes are unique and complex environments, led by teachers with limited time and resources with priorities that vary by class and the students they serve. Therefore, developing curricula about AI for classes that span many disciplines (e.g. history, art, math) must involve centering the expertise of cross-disciplinary teachers. In this study, we conducted five collaborative curricular co-design sessions with eight teachers who taught high school humanities and STEM classes. We sought to understand how teachers considered AI when it was taught in art, math, and social studies contexts, as well as opportunities and challenges they identified with incorporating AI tools into their instruction. We found that teachers considered technical skills and ethical debates around AI, opportunities for "dual exploration" between AI and disciplinary learning, and limitations of AI tools as supporting engagement and reflection but also potentially distracting. We interpreted our findings relative to co-designing adaptable AI curricula to support teaching about and with AI across high school disciplines.

Co-designing AI Education Curriculum with Cross-Disciplinary High School Teachers | VIDEO

As Artificial Intelligence (AI) continues to permeate various aspects of societies, understanding the disparities in AI knowledge and skills across different living areas becomes imperative. This study investigates the digital and AI skills gaps in the context of small and large European living areas, shedding light on the potential hindrances to unleashing the full economic and social potentials of these regions in an AI-enabled economy.
Small living areas have emerged as significant contributors to Europe's economy, offering an alternative to the bustling environment of larger cities for those seeking an improved quality of life. Nonetheless, they often encounter challenges related to digital infrastructure, access to financial resources, and digital skills gaps, limiting their economic and social growth prospects.
Drawing from a comprehensive dataset encompassing over 4,000 respondents across eight EU countries, this research examines the current perceptions and understandings of AI and digital skills within two distinct population groups: residents of smaller living areas and their counterparts in larger communities. Through bivariate analysis, notable insights are revealed concerning trust in AI solutions and entities, self-assessed digital skills, AI awareness, and attitudes in both population groups.
The findings indicate that individuals residing in smaller living areas exhibit lower trust in AI solutions and entities, alongside diminished self-perceived digital skills in comparison to those in larger communities. Notably, no significant disparities are observed in AI awareness, attitude, and self-assessed AI skills between the two groups.
Further examination of key demographic variables, including age, gender, and education, underscores intriguing relationships between these variables and AI-related perceptions and skills. In living areas with populations less than 30,000, digital skills exhibit associations with all measured variables, while gender and education correlate with specific facets of trust in AI solutions and entities. Age groups demonstrate connections solely with trust in AI solutions and entities, whereas education reveals relationships with all variables except trust in AI solutions.
On the other hand, in larger living areas, where populations are of more than 30,000, digital skills exhibit similar relationships with all measured variables, and gender again influences trust in AI solutions. Interestingly, age groups exclusively correlate with AI attitudes and trust in AI solutions and entities, omitting a link to AI awareness. Additionally, education displays connections with all variables except trust in AI solutions, mirroring patterns observed in smaller communities.
These insights underscore the significance of addressing digital and AI skills gaps in fostering growth and preparedness for the AI-driven future. As AI becomes increasingly integral to various aspects of society, targeted interventions and policies are essential to bridge these gaps and enable individuals and communities to harness the transformative potential of AI-enabled economies.

Addressing Digital and AI Skills Gaps in European Living Areas: A Comparative Analysis of Small and Large Communities

Environmental conservation organizations routinely monitor news content on conservation in protected areas to maintain situational awareness of developments that can have an environmental impact. Existing automated media monitoring systems require large amounts of data labeled by domain experts, which is only feasible at scale for high-resource languages like English. However, such tools are most needed in the global south where the news of interest is mainly in local low-resource languages, and far fewer experts are available to annotate datasets on a sustainable basis. In this paper, we propose NewsSerow, a method to automatically recognize environmental conservation content in low-resource languages. NewsSerow is a pipeline of summarization, in-context few-shot classification, and self-reflection using large language models (LLMs). Using at most 10 demonstration example news articles in Nepali, NewsSerow significantly outperforms other few-shot methods and can achieve comparable performance with models fully fine-tuned using thousands of examples. With NewsSerow, Organization X has been able to deploy the media monitoring tool in Nepal, significantly reducing their operational burden, and ensuring that AI tools for conservation actually reach the communities that need them the most. NewsSerow has also been deployed for countries with other languages like Colombia.

Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages

Flood mapping on Earth imagery is crucial for disaster management, but its efficacy is hampered by the lack of high-quality training labels. Given high-resolution Earth imagery with coarse and noisy training labels, a base deep neural network model, and a spatial knowledge base with label constraints, our problem is to infer the true high-resolution labels while training neural network parameters. Traditional methods are largely based on specific physical properties and thus fall short of capturing the rich domain constraints expressed by symbolic logic. Neural-symbolic models can capture rich domain knowledge, but existing methods do not address the unique spatial challenges inherent in flood mapping on high-resolution imagery. To fill this gap, we propose a spatial-logic-aware weakly supervised learning framework. Our framework integrates symbolic spatial logic inference into probabilistic learning in a weakly supervised setting. To reduce the time costs of logic inference on vast high-resolution pixels, we propose a multi-resolution spatial reasoning algorithm to infer true labels while training neural network parameters. Evaluations of real-world flood datasets show that our model outperforms several baselines in prediction accuracy. The code is available at \url{https://github.com/spatialdatasciencegroup/SLWSL}.

Spatial-Logic-Aware Weakly Supervised Learning for Flood Mapping on Earth Imagery

Sustainability challenges inherently involve the consideration of multiple competing objectives. The Pareto frontier – the set of all optimal solutions that cannot be improved with respect to one objective without negatively affecting another – is a crucial decision-making tool for navigating sustainability challenges as it highlights the inherent trade-offs among conflicting objectives. Our research is motivated by the strategic planning of hydropower in the Amazon basin, one of the earth’s largest and most biodiverse river systems, where the need to increase energy production coincides with the pressing requirement of minimizing detrimental environmental impacts. We investigate an innovative strategy that pairs hydropower with Floating Photovoltaic Solar Panels (FPV). We provide a new extended multi-tree network formulation, which enables the consideration of multiple dam configurations.  To address the computational challenge of scaling up the Pareto optimization framework to tackle multiple objectives across the entire Amazon basin, we further enhance the state-of-the-art algorithm for Pareto frontiers in tree-structured networks with two improvements. We introduce affine transformations induced by the sub-frontiers to compute Pareto dominance and provide strategies for merging sub-trees,  significantly increasing the pruning of dominated solutions. Our experiments demonstrate considerable speedups, in some cases by more than an order of magnitude, while maintaining optimality guarantees, thus allowing us to more effectively approximate the Pareto frontiers. Moreover, our findings suggest significant shifts towards higher energy values in the Pareto frontier when pairing hybrid hydropower with FPV solutions, potentially amplifying energy production while mitigating adverse impacts.

Scaling Up Pareto Optimization for Tree Structures with Affine Transformations: Evaluating Hybrid Floating Solar-Hydropower Systems in the Amazon

Vision Transformers (ViTs) represent self-attention-based network backbones shown to be efficient in many individual tasks, but which have not been explored in Task-Free Continual Learning (TFCL) so far. Most existing ViT-based approaches for Continual Learning (CL) are relying on task information. In this study, we explore the advantages of the ViT in a more challenging CL scenario where the task boundaries are unavailable during training. To address this learning paradigm, we propose the Task-Free Dynamic Sparse Vision Transformer (TFDSViT), which can dynamically build new sparse experts, where each expert leverages sparsity to allocate the model's capacity for capturing different information categories over time. To avoid forgetting and ensure efficiency in reusing the previously learned knowledge in subsequent learning, we propose a new dynamic dual attention mechanism consisting of the Sparse Attention (SA') and Knowledge Transfer Attention (KTA) modules. The SA' refrains from updating some previously learned attention blocks for preserving prior knowledge. The KTA uses and regulates the information flow of all previously learned experts for learning new patterns. The proposed dual attention mechanism can simultaneously relieve forgetting and promote knowledge transfer for a dynamic expansion model in a task-free manner. We also propose an energy-based dynamic expansion mechanism using the energy as a measure of novelty for the incoming samples which provides appropriate expansion signals leading to a compact network architecture for TFDSViT. Extensive empirical studies demonstrate the effectiveness of TFDSViT. The code and supplementary material (SM) are available at https://github.com/dtuzi123/TFDSViT.

Task-Free Dynamic Sparse Vision Transformer for Continual Learning

The last years have seen astonishing progress in the capabilities of generative AI techniques, particularly in the areas of language and visual understanding. Key to the success of these models is the availability of very large sets of images and text along with models that are able to digest such large datasets. Unfortunately, we have not been able to replicate this success in the context of robotics, where robots still struggle to perform seemingly simple tasks such as manipulating objects in the real world. A crucial reason for this problem is the lack of data suitable to train powerful, general models for robot decision making and control. In this talk, I will describe our ongoing efforts toward developing the models and generating the kind of data that might enable us to train foundational robot manipulation skills. To generate large amounts of demonstration data, we sample many object rearrangement tasks in physically realistic simulation environments, generate high quality solutions for them, and then train perception-driven manipulation skills that can be used in unknown, real-world environments. We believe that such skills along with generative AI reasoning can provide robots with the capabilities necessary to succeed across a wide range of applications.

Downloads

Next from AAAI 2024

OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning

Similar lecture

A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning

Similar lecture

A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction

Downloads