BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Central BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251107T143818Z UID:2F4E7B3C-363D-4C42-95C4-C0141C41A383 DTSTART;TZID=US/Central:20251106T170000 DTEND;TZID=US/Central:20251106T200000 DESCRIPTION:[]\n\nModern weather forecasting is a computationally intensive activity\, relying on expensive data sources like satellites and Doppler radar. This presentation explores an alternative\, low-cost approach using machine learning to predict local weather conditions. By leveraging histo rical METAR data (routine reports published by airports)\, we can train a deep neural network to find predictive patterns that are difficult to disc ern with other methods.\n\nThis talk will detail the complete project life cycle: from acquiring and cleansing over 7.5 million METAR records to the design\, training\, and tuning of the neural network using Pylorch. An emp hasis is placed on explaining the steps generally used to develop machine learning applications. We will cover feature engineering\, model architect ure\, and the results\, which show the model can predict temperature 30 ho urs out with a Mean Absolute Error of about 2.6°C. While not matching the precision of state-of-the-art global systems\, this method produces a rea sonably accurate forecast using minimal resources\, demonstrating the powe r of machine learning to create effective solutions without the need for s upercomputers. At the close of the talk\, we will demonstrate the tool in its current form.\n\nThis presentation will count for 1 Professional Devel opment Hour (PDH) for the PE License in Wisconsin and Michigan.\n\n[]\n\nS peaker(s): Greg Hawley \n\nAgenda: \n5:00 Featured Speaker - Greg Hawley\n \nD.J. Bordini Center at FVTC\n\n[]\n\n6:30 Adjourn to Good Company\n110 N . Richmond St.\nAppleton\, WI\n\n6:45 Social time\, cash bar open\nOrder m eals from the restaurant menu\n\n7:00 Section announcements\, door prize d rawing\n\nRoom: BC112B\, Bldg: D.J. Bordini Center at FVTC\, 5 N. Systems Drive\, Appleton\, Wisconsin\, United States\, 54914 LOCATION:Room: BC112B\, Bldg: D.J. Bordini Center at FVTC\, 5 N. Systems Dr ive\, Appleton\, Wisconsin\, United States\, 54914 ORGANIZER:blluchs@ieee.org SEQUENCE:134 SUMMARY:Weather Forecasting Using METAR Inputs Through Machine Learning: Go od Forecasts at Lower Computation and Data Acquisition Cost URL;VALUE=URI:https://events.vtools.ieee.org/m/507833 X-ALT-DESC:Description: <br /><p class="MsoNormal"><span style="font-size: 12.0pt\; line-height: 115%\; font-family: 'Aptos'\,sans-serif\; mso-ascii- theme-font: minor-latin\; mso-fareast-font-family: Aptos\; mso-fareast-the me-font: minor-latin\; mso-hansi-theme-font: minor-latin\; mso-bidi-font-f amily: 'Times New Roman'\; mso-bidi-theme-font: minor-bidi\; mso-ansi-lang uage: EN-US\; mso-fareast-language: EN-US\; mso-bidi-language: AR-SA\;">&n bsp\;<img style="display: block\; margin-left: auto\; margin-right: auto\; " src="https://events.vtools.ieee.org/vtools_ui/media/display/0a27fff0-ffb a-40b6-b430-1aec2372ca0d" alt="" width="742" height="300"></span></p>\n<p class="MsoNormal"><span style="font-size: 12.0pt\; line-height: 115%\; fon t-family: 'Aptos'\,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-fa reast-font-family: Aptos\; mso-fareast-theme-font: minor-latin\; mso-hansi -theme-font: minor-latin\; mso-bidi-font-family: 'Times New Roman'\; mso-b idi-theme-font: minor-bidi\; mso-ansi-language: EN-US\; mso-fareast-langua ge: EN-US\; mso-bidi-language: AR-SA\;">Modern weather forecasting is a co mputationally intensive activity\, relying on expensive data sources like satellites and Doppler radar. This presentation explores an alternative\, low-cost approach using machine learning to predict local weather conditio ns. By leveraging historical METAR data (routine reports published by airp orts)\, we can train a deep neural network to find predictive patterns tha t are difficult to discern with other methods.<br><br>This talk will detai l the complete project lifecycle: from acquiring and cleansing over 7.5 mi llion METAR records to the design\, training\, and tuning of the neural ne twork using Pylorch. An emphasis is placed on explaining the steps general ly used to develop machine learning applications. We will cover feature en gineering\, model architecture\, and the results\, which show the model ca n predict temperature 30 hours out with a Mean Absolute Error of about 2.6 &deg\;C. While not matching the precision of state-of-the-art global syste ms\, this method produces a reasonably accurate forecast using minimal res ources\, demonstrating the power of machine learning to create effective s olutions without the need for supercomputers. At the close of the talk\, w e will demonstrate the tool in its current form. &nbsp\;</span></p>\n<p><s pan style="font-family: arial\, helvetica\, sans-serif\; font-size: 12pt\; ">This presentation will count for 1 Professional Development Hour (PDH) f or the PE License in Wisconsin and Michigan.</span></p>\n<p><img style="di splay: block\; margin-left: auto\; margin-right: auto\;" src="https://even ts.vtools.ieee.org/vtools_ui/media/display/1fa144a7-4d04-4894-9fef-4a6ab00 d74a8" alt="" width="436" height="188"></p><br /><br />Agenda: <br /><p><s pan style="font-family: arial\, helvetica\, sans-serif\; font-size: 12pt\; ">5:00 Featured Speaker - Greg Hawley</span></p>\n<p><span style="font-fam ily: arial\, helvetica\, sans-serif\; font-size: 12pt\;">&nbsp\; &nbsp\; & nbsp\; &nbsp\; D.J. Bordini Center at FVTC<br>&nbsp\; &nbsp\; &nbsp\; &nbs p\; <img src="https://events.vtools.ieee.org/vtools_ui/media/display/bf7f5 87a-a42b-4fba-ba9c-a5e6b8094b72" width="643" height="567"></span></p>\n<p> <span style="font-family: arial\, helvetica\, sans-serif\; font-size: 12pt \;">&nbsp\; &nbsp\; &nbsp\; &nbsp\;<img src="https://events.vtools.ieee.or g/vtools_ui/media/display/c80077c0-b9ec-45ae-8545-618e6dd4df87" alt="" wid th="646" height="217"></span></p>\n<p><span style="font-family: arial\, he lvetica\, sans-serif\; font-size: 12pt\;">6:30 Adjourn to Good Company</sp an><br><span style="font-family: arial\, helvetica\, sans-serif\; font-siz e: 12pt\;">&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; 110 N. Richmond St.</span><br><sp an style="font-family: arial\, helvetica\, sans-serif\; font-size: 12pt\;" >&nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; &nbsp\; & nbsp\; &nbsp\; &nbsp\; &nbsp\; Appleton\, WI</span></p>\n<p><span style="f ont-family: arial\, helvetica\, sans-serif\; font-size: 12pt\;">6:45 Socia l time\, cash bar open</span><br><span style="font-family: arial\, helveti ca\, sans-serif\; font-size: 12pt\;">&nbsp\; &nbsp\; &nbsp\; &nbsp\; Order meals from the restaurant menu</span></p>\n<p><span style="font-family: a rial\, helvetica\, sans-serif\; font-size: 12pt\;">7:00 Section announceme nts\, door prize drawing</span><br><br></p> END:VEVENT END:VCALENDAR