HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

Title: HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

HiRO-ACEv2: 以极低成本实现 3 公里分辨率的极端天气模拟

We introduce HiRO-ACEv2, the newest update to our High Resolution Output Ai2 Climate Emulator (HiRO-ACE) system. HiROv2 can reproduce even extremely rare rain, wind, and pressure events with high accuracy, while the full system can generate global 3 km climate data at about 1/300th the cost of X-SHiELD, a high-resolution global atmospheric model that explicitly simulates storms and other small-scale weather.

我们推出了 HiRO-ACEv2，这是我们高分辨率输出 Ai2 气候模拟器 (HiRO-ACE) 系统的最新更新。HiROv2 能够以高精度重现极其罕见的降雨、风力和气压事件，而整个系统生成全球 3 公里气候数据的成本仅为 X-SHiELD 的约 1/300。X-SHiELD 是一款能够明确模拟风暴和其他小尺度天气的高分辨率全球大气模型。

HiRO-ACE, introduced earlier in 2026, has two parts: ACE, an AI model that operates at a coarser 100 km resolution, and HiRO, a model that sharpens those coarse outputs into fine 3 km detail. The biggest change in HiRO-ACEv2 is the new downscaling model, HiROv2, which can now 1) predict several high-resolution fields at once instead of just rainfall, so it can capture a much wider range of extreme weather, and 2) has improved skill in predicting extreme events.

HiRO-ACE 于 2026 年初推出，由两部分组成：ACE（一种在 100 公里粗分辨率下运行的 AI 模型）和 HiRO（一种将这些粗略输出细化为 3 公里精细细节的模型）。HiRO-ACEv2 最大的变化在于新的降尺度模型 HiROv2，它现在能够：1) 同时预测多个高分辨率场而不仅仅是降雨，从而捕捉更广泛的极端天气；2) 提高了预测极端事件的能力。

Our main focus with HiRO-ACEv2 was to simulate extreme events well. Changes to how we train HiROv2 improved its ability to reproduce the most intense rain, wind, and pressure values. When given coarsened X-SHiELD data, it matches the target simulation’s high-resolution statistics to within 3%, even for events so rare they occur only once in a million data points.

我们开发 HiRO-ACEv2 的主要重点是出色地模拟极端事件。我们对 HiROv2 训练方式的改进提升了其重现最强降雨、风力和气压数值的能力。当输入粗化后的 X-SHiELD 数据时，它与目标模拟的高分辨率统计数据匹配度在 3% 以内，即使对于百万分之一概率的罕见事件也是如此。

It also accurately estimates the total energy of tropical cyclones, including storms it never saw during training, and generates hurricanes with realistic eyes and rain bands, though winds and pressure around the eye remain somewhat more lopsided than in X-SHiELD. Additionally, HiROv2 realistically generates strong winds flowing down mountain slopes.

它还能准确估算热带气旋的总能量，包括训练期间未曾见过的风暴，并能生成具有逼真风眼和雨带的飓风，尽管风眼周围的风力和气压比 X-SHiELD 中的略显不对称。此外，HiROv2 还能逼真地模拟沿山坡下行的强风。

We also trained an updated version of ACE for this system. Over a 10-year simulation, its hurricanes, average climate patterns, and overall distributions of rain, wind, and pressure all line up well with X-SHiELD. That tells us ACE’s coarse simulations are a solid foundation for producing long-term high-resolution climate data.

我们还为该系统训练了 ACE 的更新版本。在 10 年的模拟中，其飓风、平均气候模式以及降雨、风力和气压的整体分布都与 X-SHiELD 高度吻合。这表明 ACE 的粗分辨率模拟是生成长期高分辨率气候数据的坚实基础。

Putting HiROv2 and ACE together, we generated a full year of global 3 km data. Its statistics closely match X-SHiELD’s, even though HiRO was working from a simulation ACE ran on its own rather than from real X-SHiELD data. Across a 10-year run, the energy of HiRO-ACEv2’s hurricanes is comparable to X-SHiELD’s over the same period, and snapshots from that run show a variety of other extreme events that resemble those in X-SHiELD.

将 HiROv2 和 ACE 结合使用，我们生成了整整一年的全球 3 公里分辨率数据。其统计数据与 X-SHiELD 非常接近，尽管 HiRO 使用的是 ACE 自行运行的模拟数据，而非真实的 X-SHiELD 数据。在 10 年的运行周期中，HiRO-ACEv2 飓风的能量与同期 X-SHiELD 的能量相当，且运行快照显示了各种类似于 X-SHiELD 中的其他极端事件。

Overall, HiRO-ACEv2 offers researchers a flexible and inexpensive way to generate many versions of high-resolution rain, wind, and pressure data for extreme events over 10 years or more. Producing global high-resolution data with it costs roughly 300 times less than running X-SHiELD. If only one region is needed, the savings can be more than a hundred times greater, depending on the size of the area.

总的来说，HiRO-ACEv2 为研究人员提供了一种灵活且低成本的方法，用于生成 10 年或更长时间内极端事件的高分辨率降雨、风力和气压数据。使用该系统生成全球高分辨率数据的成本大约是运行 X-SHiELD 的 300 分之一。如果仅需特定区域的数据，根据面积大小，节省的成本甚至可以再增加一百倍以上。

We’re also working on a streamlined version of HiROv2 that could make it more than ten times faster still. We still have future work ahead of us: because HiRO learned from X-SHiELD, it only works with the version of ACE tuned to match X-SHiELD. That means it can’t yet produce high-resolution data for other climates, such as a warmer future or the historical record in datasets like ERA5.

我们还在开发 HiROv2 的精简版，其速度有望再提升十倍以上。我们未来仍有工作要做：由于 HiRO 是从 X-SHiELD 学习的，它目前仅适用于为匹配 X-SHiELD 而调整的 ACE 版本。这意味着它还无法为其他气候场景（如更温暖的未来或 ERA5 等数据集中的历史记录）生成高分辨率数据。

Next, we plan to train on new X-SHiELD datasets, including one simulating a world 4°C warmer, so the system can handle different climates. We also plan to add outputs like near-surface temperature and snow and ice, which would allow for even more uses, such as snowpack prediction.

接下来，我们计划在新的 X-SHiELD 数据集上进行训练，包括模拟全球升温 4°C 的数据集，以便系统能够处理不同的气候条件。我们还计划增加近地表温度、积雪和冰层等输出，这将使其能够应用于更多领域，例如积雪预测。