type
status
date
slug
summary
tags
category
icon
password
参考原稿
Why do cumulus clouds have well defined boundaries? In other words, what are the physical mechanisms that hold a cloud together, as an entity separate from other clouds, that prevent it from spreading, etc.
Naively, one could expect the atmospheric vapour to spread homogeneously or (in presence of nonlinearities inherent in hydrodynamics) form periodic structures or even vortices - these are indeed observed (see, e.g., horizontal convective rolls), but does not seem to explain the cumulus clouds. Dust clouds in outer space, held together by gravity seem closer phenomenologically, but physically gravity seems as a less plausible explanation than fluid/gas dynamics
Clouds are fuzzier than they look.
Clouds get their white colour from Mie scattering of light from water droplets of size comparable to the wavelength of light. But for smaller droplets Rayleigh scattering is the best approximation. The formula for the intensity of that radiation seen by an observer at distance R, scattering angle θ, wavelength λ from a particle of refractive index n with diameter d is
Note the last term: the scattering intensity increases with the sixth power of the diameter. That means that as the vapour density increases in the air and droplets start forming, even a completely smooth gradient of droplet sizes will look like it has a sharp edge where the scattering goes from minuscule to dominant.
Once droplets are ∼10% of the light wavelength the full Mie theory is needed, but the effect is roughly the same (and less wavelength dependent).
There are doubtless other forces keeping cumulus clouds sharp, like the upper boundary often corresponding to the top of an upwelling convective flow into drier air and hence having a strong vapour gradient, and the cloud base being set by temperature, pressure and the dew point.
I just want to expand on Anders’s otherwise great answer, because I think based on the text of the question this paragraph is more what you're asking for:
There are doubtless other forces keeping cumulus clouds sharp, like the upper boundary often corresponding to the top of an upwelling convective flow into drier air and hence having a strong vapour gradient, and the cloud base being set by temperature, pressure and the dew point.
What the layperson needs to understand about a cloud, is that it is not like a rock with a defined set of grains/crystals in a fixed configuration. It is more like a river or a waterfall. Stuff is coming in one end and going out the other.
At the bottom you have moist air coming upwards, where the water inside is fully vaporized and so is transparent. But the pressure is dropping and so is the temperature, and at a particular virtual boundary which is the flat bottom of the cloud, this vaporized water condenses into little droplets. Those droplets are visible now.
All of the little droplets that you are seeing in the cloud are drifting, and on average they are drifting upwards.
Partly this is driven by outside factors, different masses of air moving across the landscape collide and one of them shifts upwards while the other one burrows underneath. But it is also self-sustaining. As a consequence of condensing, droplets release heat which warms the air which expands it. The warm air rises and drags the droplet with it upwards. Because the flows involved are way slower than the speed of sound, the air behaves approximately as an incompressible fluid. That just means that if there is this sudden updraft from the condensation warming the air, then air gets sucked in from the bottom to prevent a vacuum. (Incompressible also means not expandable, the vacuum can be interpreted as “stretching out the air” and at lower velocities air doesn't like to stretch.)
Eventually the droplet leaves the moist air that it is in. If it leaves out of the sides of the cloud, or the bottom, it may re-evaporate. On the other hand if it leaves out of the top of the cloud, which usually requires some pretty considerable convective wind transport, then it may get to the upper atmosphere where it can spontaneously freeze into “diamond dust”, tiny little flecks of supercooled ice. These are cirrus clouds, and they look a lot more fuzzy and flowy. A cumulus cloud that does this with those strong convective currents is a cumulonimbus cloud, a rain cloud. They have a characteristic anvil-like shape from the diamond dust top spreading out while the bottom is so firm and solid. (And the rain comes of course from the super-cooled ice crystals coming back down into the cloud, growing into big snowflakes, falling out of the cloud, and melting into raindrops.)
If you've been out on a foggy day then you have walked around in a cloud before, they do not have extremely sharp boundaries when you are up close in person. But, these very common cumulus clouds have this distinctive flat bottom and puffy top because those represent properties of the surrounding air where the droplets are appearing and disappearing. The bottom is flat because the dominant temperature and pressure gradient is vertical, the top is poofy with a sharp-looking boundary because you are looking at this boundary where this moist air mass from below collides with a dry air mass which it is pushing, roiling, bubbling into. The droplets at the one boundary are either turned away or evaporated into the dry air, the droplets at the other boundary are formed and are pulling more moist air up after them.
AI讲解
云朵的边缘有时看起来锐利，有时则模糊，这取决于光学效应和大气物理过程的结合。由于你具备高中物理（包括热力学、流体力学和光学基础）和大学高等数学（有助于理解梯度、非线性和散射公式）的背景，我将一步步用中文解释，基于你提供的文章。我们以积云（cumulus clouds）作为“边缘锐利”的例子，并与模糊的云（如卷云）对比。
1. 光学错觉：为什么云看起来比实际更锐利
即使云与晴空之间的过渡在物理上并非完全突兀，从远处看也常常显得锐利。这源于光与水滴的散射作用，你可能从基础光学中回忆起类似概念。
- 瑞利散射和米氏散射基础：云的白色来自于阳光在水滴上的散射。对于非常小的水滴（远小于可见光波长 λ ≈ 400–700 nm），瑞利散射（Rayleigh scattering）占主导。散射强度 I 的公式大致为：
（其中 d 是水滴直径，其他项包括距离 R、散射角 θ 和折射率 n）。关键在于 d^6 项：随着水滴稍稍变大，散射强度急剧增加。
- 为什么这会产生锐利边缘：云形成时，水蒸气在空气冷却时逐渐凝结成水滴。你可能期望水滴大小和密度的梯度是平滑的、扩散的。但由于六次方依赖，即使是温和的 d 增加，也会让散射从微不足道（不可见的蒸气）跃升到主导（明亮的白色云）。数学上，如果 d 加倍，I 会增加 64 倍！因此，从远处看，本来模糊的过渡显得像一个清晰的边界，云“开始”的地方。
- 向米氏散射的过渡：对于较大的水滴（约 λ 的 10% 或更大，如 0.05–1 μm），需用米氏理论（Mie theory，更复杂，涉及麦克斯韦方程的球面波解，但你无需完整数学）。它对波长的依赖较小（蓝色调减少），但仍随大小急剧放大，强化边缘效应。
这种光学技巧解释了为什么许多云看起来比直接观察蒸气分布时更锐利。近距离（如雾中，这是地面云），边界感觉更模糊，因为你身处梯度之中。
2. 物理机制：什么让积云作为独立实体保持在一起
你天真地期望大气蒸气均匀扩散或形成周期结构（如涡旋或水平对流卷），这对某些大气现象是正确的，但积云由流体力学和热力学的动态、非平衡过程塑造。它们不像星际尘云那样由重力维系，而是大气中的“事件”，由对流和相变维持。
- 云作为动态流动（像河流或瀑布）：不像固体岩石，积云不是固定水滴集合——它是一个流通系统。湿空气从下方上升（因地面加热或空气团碰撞），绝热冷却（高度增加压力降低，遵循理想气体定律和递减率），达到露点。在这个“虚拟边界”（平坦的云底），蒸气凝结成可见水滴，释放潜热。
这热量加热周围空气，使其浮力增加（密度降低，按阿基米德原理）。热空气进一步上升，形成上涌气流，拉入更多下方湿空气——自维持对流。由于空气流动亚音速（远低于声速 ~340 m/s），大气近似不可压缩（低速下体积变化小）。这意味着上涌气流会从下方吸入空气，避免真空，并保持流动有序。
- 锐利边界来自梯度：
- 底部边缘（平坦且锐利）：由温度、压力和湿度的垂直梯度均匀设定。露点在稳定层中大致同一高度达到，因此凝结突然开始，形成平坦底部。水滴在此形成，并平均向上漂移。
- 顶部和侧面（蓬松但看似锐利）：上边界是上升湿空气撞击上方干燥空气的地方，产生强蒸气梯度。湿空气“冒泡”进入干燥层，像沸水翻滚（非线性流体力学，涉及不同密度流体界面处的瑞利-泰勒不稳定性）。如果水滴偏离进入干燥空气（侧面或顶部），会快速蒸发，锐化边缘。这不是重力主导；是流体混合被对流胞结构抵抗。
- 防止扩散：云不均匀扩散，因为上涌气流将其限制——像喷泉向上喷水而不四处溅射。非线性（如湍流）产生蓬松凸起，但整体形状因持续流动保持连贯。如果对流减弱，云就消散。
- 与其他结构的比较：你提到周期卷或涡旋——这些确实发生（如边界层中的水平对流卷），但积云形成于不稳定、垂直深的对流胞中（像加热流体中的贝纳胞，放大版）。重力起次要作用（浮力），主要是气体动力学和相变。
3. 为什么有些云模糊（不锐利）
并非所有云都有积云般的锐利；取决于形成机制：
- 模糊云（如卷云或层云）：在温和条件下形成。卷云是高空冰晶（“钻石尘”），来自过冷水自发冻结。它们在稳定层中水平扩散，梯度较弱，流动不局限，因此边缘模糊。没有强上涌意味着较少“维系在一起”。层云（雾状层云）有平滑、扩散边界，因为它们在稳定、分层空气中，无锐利露点过渡。
- 锐利 vs. 模糊例子：
- 积雨云（雷暴云）：底部如积云般锐利，但顶部呈砧状，因冰在高风中扩散——仍distinct但有模糊延伸。
- 雾：四周模糊，因为近地面，垂直结构最小。
总之，积云的明确边界源于光学锐化（散射放大小梯度）和物理限制（对流上涌、蒸气梯度及相变热释放创建自维持流动）。它们不是像固体那样“维系”，而是作为动态实体维持。模糊云缺乏这些强梯度或局限对流。
我的理解
如果颜色变化很慢，会觉得过渡模糊。但如果在某个点颜色突然“亮起来”很多倍（比如从几乎透明到超级白），从远处看就好像有个sharp的边缘。
云里的水滴从小到大形成。小的水滴几乎不散射光（像隐形的蒸气），大的水滴突然把阳光反射得超级亮（白色云）。即使水滴密度是慢慢增加的，这种“亮度爆炸”让边界看起来像刀切一样锐利(从公式可知)。从远处看，云像个棉花糖；但近看（如走在雾里），会发现它其实渐变模糊，没那么分明。
那么云为什么不扩散成一团乱，而是保持形状？
热空气从地面升起，像煮开水时的气泡。空气上升时冷却，到一定高度，水蒸气突然凝结成可见水滴。这高度在周围差不多一样，所以底部像个平底锅——锐利且平。
上升的湿空气撞上上方的干空气，像热水倒进冷水里，会翻滚但不随便混。湿空气里的水滴如果“跑出去”到干区，就马上蒸发掉。云靠热量自维持——凝结放热，让空气更热、更轻，继续上升，拉更多空气进来。像循环泵，不让云摊开成薄雾。
现实中的力学远比想象的复杂，很多问题穷极根本其实到了很深的理论，然而这里“浅尝辄止”，知足常乐。