Update HART-SURYA_README.md

HART-SURYA_README.md

@@ -1,6 +1,15 @@
+This HART-SURYA proposal is made in response to the article that I received mention of in an email today.
+See e.g., 
+https://science.nasa.gov/science-research/artificial-intelligence-model-heliophysics/?utm_source=whatsupinai.beehiiv.com&utm_medium=newsletter&utm_campaign=pixel-as-the-true-ai-first-smartphone-nasa-ibm-reveal-surya-gemini-replaces-assistant-on-nest-devices
+https://science.data.nasa.gov/features-events/inside-surya-solar-ai-model
+See 
+https://huggingface.co/nasa-ibm-ai4science/Surya-1.0/blob/main/README.md
+and   
+https://github.com/NASA-IMPACT/Surya/blob/main/README.md
+
 I examined the patchifying and positional encoding and tokenization methods employed in the Surya model. 
 
-I posted these proposals for Surya model upgrades at https://github.com/NASA-IMPACT/Surya/issues/21
+I posted the following proposals for Surya model upgrades at https://github.com/NASA-IMPACT/Surya/issues/21
 
 I find the input/tokenization method to be surprisingly simple, and perhaps inefficient.   It seems that the transformer model is receiving square images centered about the sun and containing much dark space around the sun that contains no information.  Although a transformer model is smart and can figure things out, it is usually better to optimize the inputs to reduce noise and remove extraneous data that only consumes compute and power (garbage in, garbage out) and adds nothing to the best results.