The station-density confidence mask

The CNN refinement is not applied uniformly. A confidence field, built from the smoothed density of the CPC-UNI gauges, gates the blend: where gauges are dense the CNN contributes, where they are sparse the product falls back to pure LSEQM. This keeps the data-hungry step honest about where it has support.

Where the gauges are - and where the CNN activates

Confidence over the 0.1° land grid (Gaussian-smoothed, σ ≈ km); the gauges are overlaid as white dots. The network is heavily concentrated in Java - so is the confidence.

0 · pure LSEQM

· max

Max confidence

of 1.0 (dense Java)

Max DL weight

% where densest

Mean DL weight

% over all land

Land the CNN touches

% at any weight

The mask never reaches full confidence: even the densest cell tops out at , so the CNN's share peaks near % in Java and averages just % across Indonesia. The refinement is real but deliberately restrained.

How confidence sets the blend

The blend weight is a straight line in confidence:

effective α = 1 − confidence × (1 − ) → CNN weight = confidence ×

Confidence 0 gives α = 1.0 (pure LSEQM, no CNN); confidence 1 would give α = (30% CNN). The dashed line marks the mask's actual ceiling.

What if the saturation count changed?

Confidence saturates at DENSITY_SATURATION_COUNT smoothed stations per cell (default ). That threshold was set by judgement, not optimised - it is one of the sensitivity parameters. Lowering it lets sparser networks reach full confidence, activating more CNN; raising it is more conservative. Drag it to see the effect on the same mask.

Mean CNN weight

% over all land

Max CNN weight

% in the densest cell

Land with CNN ≥ 10%

At the default of , the mean weight is % and almost no land clears a 10% CNN share - the conservative choice the thesis flags as a limitation. Dropping the count toward 1 concentrates more correction into the same Java-centred pattern rather than spreading it east, because the underlying gauge network, not the threshold, is what is sparse.