MAROKO133 Hot ai: Forests Are Steadily Crawling North, Satellite Imagery Shows Terbaru 202

📌 MAROKO133 Update ai: Forests Are Steadily Crawling North, Satellite Imagery Show

Climate change is leaving plenty of dramatic reminders behind as it reshapes our planet, from rapidly retreating glaciers to more frequent extreme weather events.

Forests are also bearing the brunt of global warming. Scientists recently examined satellite data ranging from 1985 to 2020 and made a striking discovery: that boreal forests, the largest terrestrial biome on Earth — and which are warming faster than any other type of forest — are steadily shifting northwards as they retreat from the heat.

Boreal forests play a key role as one of the world’s largest terrestrial carbon sinks. But how much longer they can sequester excess greenhouse gases in the atmosphere remains uncertain as global temperatures continue to rise.

As detailed in a new study published in the journal Biogeosciences, an international team of researchers — including from NASA’s Goddard Space Flight Center — analyzed imagery from the space agency’s Landsat satellites.

They created a detailed map of tree cover at a resolution of 100 feet to track changes over a 36-year time span. The finding was stark: that boreal forests not only had grown by 12 percent, but had shifted northward by 0.29 degrees of mean latitude.

“These findings confirm the northward advance of the boreal forest and implicate the future importance of the region’s greening to the global carbon budget,” they concluded in their paper.

The implications these changes have on climate change and the future of our planet are nuanced, given the degree of complexity involved. On one hand, a growth in young boreal trees could allow the forests to soak up more carbon in the atmosphere, an estimated 1.1 to 5.9 gigatonnes. To put that number into perspective, all of the world’s trees hold approximately 861 gigatonnes of carbon.

“These changes are not only spatially extensive but demographically consequential: they reflect a growing fraction of young forests with distinct structural and functional attributes that position them as dynamic agents of carbon sequestration,” the team wrote in their paper. “Understanding the contribution of these forests to current and future carbon stocks is essential for anticipating the net climate feedbacks emerging from boreal ecosystems.”

At the same time, an increasingly extreme climate could complicate the picture, sparking enormous wildfires across western Canada as outbreaks of destructive species like the bark beetle cause major losses of pine boreal forests.

Scientists are warning that shorter winters and hotter temperatures in the summer are also resulting in longer dry spells that can cause soils to dry out and harmful algae blooms to form in lakes.

In short, boreal forests may be growing and allowing them to suck up more greenhouse gases, but climate change is also putting them at a much higher risk of tree cover loss due to drought, wildfires, diseases, insect outbreaks, and so on, potentially offsetting any long-term benefits.

“Although the net trends are globally significant, they mask substantial geographic and temporal heterogeneity, as well as complexity in the ecological processes underlying forest change,” the researchers concluded.

“A more complete understanding of boreal forest dynamics will require integration of satellite time series with field-based measurements of canopy structure and the environmental drivers of growth, mortality, and species turnover,” they wrote. “Moreover, translating the resulting information into action to forestall and adapt to climate change will require effective communication across scientific, government, and commercial domains of human activity.”

More on climate change: Plants and Forests Absorbed Almost No Carbon Last Year, Shocking Climate Scientists

The post Forests Are Steadily Crawling North, Satellite Imagery Shows appeared first on Futurism.

🔗 Sumber: futurism.com

📌 MAROKO133 Hot ai: ByteDance Introduces Astra: A Dual-Model Architecture for Auto

The increasing integration of robots across various sectors, from industrial manufacturing to daily life, highlights a growing need for advanced navigation systems. However, contemporary robot navigation systems face significant challenges in diverse and complex indoor environments, exposing the limitations of traditional approaches. Addressing the fundamental questions of “Where am I?”, “Where am I going?”, and “How do I get there?”, ByteDance has developed Astra, an innovative dual-model architecture designed to overcome these traditional navigation bottlenecks and enable general-purpose mobile robots.

Traditional navigation systems typically consist of multiple, smaller, and often rule-based modules to handle the core challenges of target localization, self-localization, and path planning. Target localization involves understanding natural language or image cues to pinpoint a destination on a map. Self-localization requires a robot to determine its precise position within a map, especially challenging in repetitive environments like warehouses where traditional methods often rely on artificial landmarks (e.g., QR codes). Path planning further divides into global planning for rough route generation and local planning for real-time obstacle avoidance and reaching intermediate waypoints.

While foundation models have shown promise in integrating smaller models to tackle broader tasks, the optimal number of models and their effective integration for comprehensive navigation remained an open question.

ByteDance’s Astra, detailed in their paper “Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning” (website: https://astra-mobility.github.io/), addresses these limitations. Following the System 1/System 2 paradigm, Astra features two primary sub-models: Astra-Global and Astra-Local. Astra-Global handles low-frequency tasks like target and self-localization, while Astra-Local manages high-frequency tasks such as local path planning and odometry estimation. This architecture promises to revolutionize how robots navigate complex indoor spaces.

Astra-Global: The Intelligent Brain for Global Localization

Astra-Global serves as the intelligent core of the Astra architecture, responsible for critical low-frequency tasks: self-localization and target localization. It functions as a Multimodal Large Language Model (MLLM), adept at processing both visual and linguistic inputs to achieve precise global positioning within a map. Its strength lies in utilizing a hybrid topological-semantic graph as contextual input, allowing the model to accurately locate positions based on query images or text prompts.

The construction of this robust localization system begins with offline mapping. The research team developed an offline method to build a hybrid topological-semantic graph G=(V,E,L):

• V (Nodes): Keyframes, obtained by temporal downsampling of input video and SfM-estimated 6-Degrees-of-Freedom (DoF) camera poses, act as nodes encoding camera poses and landmark references.
• E (Edges): Undirected edges establish connectivity based on relative node poses, crucial for global path planning.
• L (Landmarks): Semantic landmark information is extracted by Astra-Global from visual data at each node, enriching the map’s semantic understanding. These landmarks store semantic attributes and are connected to multiple nodes via co-visibility relationships.

In practical localization, Astra-Global’s self-localization and target localization capabilities leverage a coarse-to-fine two-stage process for visual-language localization. The coarse stage analyzes input images and localization prompts, detects landmarks, establishes correspondence with a pre-built landmark map, and filters candidates based on visual consistency. The fine stage then uses the query image and coarse output to sample reference map nodes from the offline map, comparing their visual and positional information to directly output the predicted pose.

For language-based target localization, the model interprets natural language instructions, identifies relevant landmarks using their functional descriptions within the map, and then leverages landmark-to-node association mechanisms to locate relevant nodes, retrieving target images and 6-DoF poses.

To empower Astra-Global with robust localization abilities, the team employed a meticulous training methodology. Using Qwen2.5-VL as the backbone, they combined Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). SFT involved diverse datasets for various tasks, including coarse and fine localization, co-visibility detection, and motion trend estimation. In the GRPO phase, a rule-based reward function (including format, landmark extraction, map matching, and extra landmark rewards) was used to train for visual-language localization. Experiments showed GRPO significantly improved Astra-Global’s zero-shot generalization, achieving 99.9% localization accuracy in unseen home environments, surpassing SFT-only methods.

Astra-Local: The Intelligent Assistant for Local Planning

Astra-Local acts as the intelligent assistant for Astra’s high-frequency tasks, a multi-task network capable of efficiently generating local paths and accurately estimating odometry from sensor data. Its architecture comprises three core components: a 4D spatio-temporal encoder, a planning head, and an odometry head.

The 4D spatio-temporal encoder replaces traditional mobile stack perception and prediction modules. It begins with a 3D spatial encoder that processes N omnidirectional images through a Vision Transformer (ViT) and Lift-Splat-Shoot to convert 2D image features into 3D voxel features. This 3D encoder is trained using self-supervised learning via 3D volumetric differentiable neural rendering. The 4D spatio-temporal encoder then builds upon the 3D encoder, taking past voxel features and future timestamps as input to predict future voxel features through ResNet and DiT modules, providing current and future environmental representations for planning and odometry.

The planning head, based on pre-trained 4D features, robot speed, and task information, generates executable trajectories using Transformer-based flow matching. To prevent collisions, the planning head incorporates a masked ESDF loss (Euclidean Signed Distance Field). This loss calculates the ESDF of a 3D occupancy map and applies a 2D ground truth trajectory mask, significantly reducing collision rates. Experiments demonstrate its superior performance in collision rate and overall score on out-of-distribution (OOD) datasets compared to other methods.

The odometry head predicts the robot’s relative pose using current and past 4D features and additional sensor data (e.g., IMU, wheel data). It trains a Transformer model to fuse information from different sensors. Each sensor modality is processed by a specific tokenizer, combined with modality embeddings and temporal positional embeddi…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com