I'll do my best to keep this simple for those not too knowledgeable about photography and the same would go for video.
First off, your water photo... there is a huge dynamic range going on here and no single image shot, with any filters will be able to manage that range. What that means is that the range from white to black or light to dark areas of the image, are so far apart that it is not possible to get them all correctly exposed in a single shot, or video frame.
The only filter that could have helped you in that particular shot, at that particular angle to the sun, would be a polarizing filter. A PL filter would have eliminated, for the most part, all those white areas in the water and made the water look a little more colourful. With that said, you must understand that a PL filter can only work when it is facing a certain angle to the sun. Once it moves away, in either direction, the PL filter will have less and less affect, on the lighting situation with regards to specular highlights and the angle of the sun to your camera and subject matter.
Regarding ND filter, as Meta4 has correctly stated, these filters are for the most part, useless to drone still shots and for a large part if not almost of all situations, when using video with your drone. I say that because an ND filter is only useful when you know how, why and when to use it. If you don't know those three things, then you don't need to be putting it on your camera.
The ND filter is used to bring shutter speed down to create a particular effect with video, regarding frame rate and shutter speed for a particular visual effect. There is far too much hype on forums and YouTube about the need for ND filters and for most average flyer/filmers, they are best left off, in order not to confuse the photographer/flyer. When you really understand filming and exposure/frame rates/required shutter speeds, that will be the time for you to delve into the depths of ND filter use, to achieve particular things while filming.
Back to dynamic range once more. Your eye has an incredible dynamic range and one that no camera made today, can possibly come close to matching. Therefore, when you look at a scene that has a high dynamic range, no camera can match the range light and dark that you are seeing.
To get a better idea of what the average camera is capable of recoding, look at a HDR scene and not the range of shadow and bright areas that you are capable of seeing, then squint your eye rather hard and notice now how those dark areas you could see before, are now looking rather closer to the black side. That is what your camera is capable of seeing. It is very poor, compared to your eye.
To help a camera expose a scene in the same way your eye can see it, the only way you could do this is with still shots and only by shooting at least five shots of the same thing, but with five different exposures. So, the first shot being very dark or under exposed and the fifth shot being very light or over exposed and all the shots in between were different exposure setting, capturing varying degrees of light and dark exposure between your two end shots
You then need to sandwich those 5 or more frames on top of each other and using something like Photoshop, go into each layer of the sandwich, which would be your varying exposures, and remove all the bits from each shot that were either too bright or too dark to be of use in the final image. I hope you have been able to understand this, so far. Feel free to ask any questions.
When done correctly you should arrive at a finished image that now gives you the total dynamic range or close to it, that you were able to see with your eye. You can forget about doing this with a video, it is only possible with still shots. There will be scenes that are simply not possible to correctly expose, due to their large dynamic range, so don't think you can always get the shot.
Filters such as ND and PL are there to aid you in your creation of an image or bit of filmed video, in the same way that spices are in the kitchen to help a chef make a great dinner. If you have no idea how to use those spices when cooking, you will not end up with a great tasting dinner. In the same way that if you have no idea how and when to use your filters, you will not end up with a well exposed still image or bit of video.
Or like a painter, if you have a wide range of paint colours before you and choice of paint brushes and canvas types, only and artist that knows how to use them, correctly combined, will be able to create a beautiful painting on their blank canvas. Someone who has no idea how and when to use what paint colour and what brush on what substrate, will just sit there in total confusion. And this is where you are currently with your camera and those filters.
Just go out and play with your drone and camera and see what you are getting in its basic form. As you learn more you can then start to play around with filters and camera settings, as you gain knowledge in what each filter and camera setting change does, in order to achieve the vision you see in your mind. Hope this helped.