Building management system with indoor air quality management using outdoor air quality forecasting

1 . A building management system for monitoring or controlling air quality of a building, the building management system including one or more computer-readable storage media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:

obtain, from a regional air quality data source, a first set of outdoor air quality data, wherein the first set of outdoor air quality data represents air quality measured for a region including the building or proximate to the building;

obtain, from one or more local sensors coupled to or positioned proximate to the building, a second set of outdoor air quality data, wherein the second set of outdoor air quality data represents air quality measurements at one or more positions at or near an exterior of the building;

execute a model, using the first set of outdoor air quality data and the second set of outdoor air quality data as input to generate an air quality assessment for the building based at least on determining a correlation factor between the first set of outdoor air quality data and the second set of outdoor air quality data, wherein executing the model to generate the air quality assessment for the building includes:

executing the model, using at least a portion of the first set of outdoor air quality data and at least a portion of the second set of outdoor air quality data as inputs to the model, to:

determine, based on a comparison of at least the portion of the first set of outdoor air quality data and at least a portion of the second set of outdoor air quality data, a weight metric correlating at least the portion of the first set of outdoor air quality data with at least the portion of the second set of outdoor air quality data; and

generate, using the weight metric, a predicted air quality value for the building; and

wherein the model is trained using data correlating local air quality data with regional air quality data;

wherein the predicted air quality value for the building is determined relative to outdoor air quality proximate to the building; and

control, based at least on the air quality assessment, one or more building systems to affect the air quality within the building, by implementing one or more control actions.

2 . The building management system of claim 1 , wherein the instructions further cause the one or more processors to:

obtain, from the regional air quality data source, a plurality of future air quality values for the region including the building or proximate to the building, wherein a first future air quality value of the plurality of future air quality values corresponds to a given first point in time and a second future air quality value of the plurality of future air quality values corresponds to a given second point in time, and wherein the plurality of future air quality values are generated by a regional model;

obtain, from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data corresponds to the given first point in time;

determine, using the first future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a localized air quality value for the building at the given first point in time; and

generate, using the second future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a second localized air quality value for the building for the given second point in time, wherein the second localized air quality value for the building is a predicted value.

3 . The building management system of claim 1 , wherein the air quality assessment for the building includes a predicted indoor air quality value for the building for a future point in time, and wherein the instructions further cause the one or more processors to:

obtain, from the regional air quality data source, a predicted outdoor air quality value for the region including the building or proximate to the building, wherein the predicted outdoor air quality value for the region is generated by a regional model and the predicted outdoor air quality value for the region pertains to the future point in time;

obtain, from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data pertains to outdoor air quality data prior to the future point in time;

update, using at least a portion of the third set of outdoor air quality data and the predicted outdoor air quality value for the region, the predicted indoor air quality value for the building for the future point in time; and

determine, using a fourth set of outdoor air quality data, an actual air quality value for the building at the future point in time, wherein the actual air quality value for the building at the future point in time is used to update the regional model that generated the predicted outdoor air quality value for the region.

4 . The building management system of claim 1 , wherein the air quality assessment for the building includes an air quality value for the building, and wherein the instructions further cause the one or more processors to:

generate, using the air quality value for the building, a plurality of recommendations, the plurality of recommendations including a plurality of control actions to improve the air quality value for the building;

provide, to a user device, the plurality of recommendations;

receive, from the user device, a selection of a first recommendation of the plurality of recommendations; and

implement, responsive to receiving the selection of the first recommendation of the plurality of recommendations, control actions included in the first recommendation of the plurality of recommendations.

5 . The building management system of claim 1 , wherein:

the air quality assessment comprises a prediction of at least one of outdoor air quality or indoor air quality for the building at one or more future times; and

the first set of outdoor air quality data comprises data based on measurements from a measurement station of a weather service.

6 . The building management system of claim 1 , wherein:

the air quality assessment comprises an uncertainty assessment indicating a level of accuracy of the first set of outdoor air quality data or the second set of outdoor air quality data; and

the air quality assessment comprises a recommendation to install one or more second local sensors to improve accuracy of the second set of outdoor air quality data.

7 . The building management system of claim 1 , wherein the air quality assessment comprises an uncertainty map indicating levels of accuracy of the first set of outdoor air quality data for a plurality of different regions, and wherein the instructions further cause the one or more processors to:

generate a customer interest map indicating customer interest in air quality information;

generate a combination of the uncertainty map and the customer interest map;

identify, using the combination of the uncertainty map and the customer interest map, one or more first areas having a customer interest in air quality information where the level of accuracy of the first set of outdoor air quality data is below a certain level; and

generate a recommendation to install one or more second local sensors for one or more buildings in the one or more first areas.

8 . The building management system of claim 1 , wherein the instructions further cause the one or more processors to:

assess how representative one or more locations of the one or more local sensors are of an overall outdoor air quality of the building; and

generate, responsive to assessing how representative the one or more locations of the one or more local sensors are of the overall outdoor air quality of the building, a recommendation to install one or more second local sensors.

9 . The building management system of claim 1 , wherein implementing the one or more control actions comprises generating the one or more control actions automatically using the air quality assessment or receiving at least one input from a user corresponding to the air quality assessment.

10 . A method for monitoring or controlling air quality of a building, the method comprising:

obtaining, by one or more processors from a regional air quality data source, a first set of outdoor air quality data, wherein the first set of outdoor air quality data represents air quality measured for a region including the building or proximate to the building;

obtaining, by the one or more processors from one or more local sensors coupled to or positioned proximate to the building, a second set of outdoor air quality data, wherein the second set of outdoor air quality data represents air quality measurements at one or more positions at or near an exterior of the building;

executing by the one or more processors, a model using the first set of outdoor air quality data and the second set of outdoor air quality data as input to generate an air quality assessment for the building based at least on determining a correlation factor between the first set of outdoor air quality data and the second set of outdoor air quality data, wherein executing the model to generate the air quality assessment for the building includes:

executing the model, using at least a portion of the first set of outdoor air quality data and at least a portion of the second set of outdoor air quality data as inputs to the model, to:

determine, based on a comparison of at least the portion of the first set of outdoor air quality data and at least the portion of the second set of outdoor air quality data, a weight metric correlating at least the portion of the first set of outdoor air quality data with at least the portion of the second set of outdoor air quality data; and

generate, using the weight metric, a predicted air quality value for the building;

wherein the model is trained using data correlating local air quality data with regional air quality data;

wherein the predicted air quality value for the building is determined relative to outdoor air quality proximate to the building; and

controlling, based at least on the air quality assessment, one or more building systems to affect the air quality within the building, by implementing one or more control actions.

11 . The method of claim 10 , further comprising:

obtaining, by the one or more processors from the regional air quality data source, a plurality of future air quality values for the region including the building or proximate to the building, wherein a first future air quality value of the plurality of future air quality values corresponds to a given first point in time and a second future air quality value of the plurality of future air quality values corresponds to a given second point in time, and wherein the plurality of future air quality values are generated by a regional model;

obtaining, by the one or more processors from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data corresponds to the given first point in time;

determining, by the one or more processors using the first future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a localized air quality value for the building at the given first point in time; and

generating, by the one or more processors using the second future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a second localized air quality value for the building for the given second point in time, wherein the second localized air quality value for the building is a predicted value.

12 . The method of claim 10 , wherein the air quality assessment for the building includes a predicted indoor air quality value for the building for a future point in time, and further comprising:

obtaining, by the one or more processors from the regional air quality data source, a predicted outdoor air quality value for the region including the building or proximate to the building, wherein the predicted outdoor air quality value for the region is generated by a regional model and the predicted outdoor air quality value for the region pertains to the future point in time;

obtaining, by the one or more processors from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data pertains to outdoor air quality data prior to the future point in time;

updating, by the one or more processors using at least a portion of the third set of outdoor air quality data and the predicted outdoor air quality value for the region, the predicted indoor air quality value for the building for the future point in time; and

determining, by the one or more processors using a fourth set of outdoor air quality data, an actual air quality value for the building at the future point in time, wherein the actual air quality value for the building at the future point in time is used to update the regional model that generated the predicted outdoor air quality value for the region.

13 . The method of claim 10 , wherein the air quality assessment for the building includes an air quality value for the building, and further comprising:

generating, by the one or more processors using the air quality value for the building, a plurality of recommendations, the plurality of recommendations including a plurality of control actions to improve the air quality value for the building;

providing, by the one or more processors to a user device, the plurality of recommendations;

receiving, by the one or more processors from the user device, a selection of a first recommendation of the plurality of recommendations; and

implementing, by the one or more processors responsive to receiving the selection of the first recommendation of the plurality of recommendations, control actions included in the first recommendation of the plurality of recommendations.

14 . The method of claim 10 , wherein:

the air quality assessment comprises an uncertainty assessment indicating a level of accuracy of the first set of outdoor air quality data or the second set of outdoor air quality data; and

the air quality assessment comprises a recommendation to install one or more second local sensors to improve accuracy of the second set of outdoor air quality data.

15 . The method of claim 10 , wherein the air quality assessment comprises an uncertainty map indicating levels of accuracy of the first set of outdoor air quality data for a plurality of different regions, and further comprising:

generating, by the one or more processors, a customer interest map indicating customer interest in air quality information;

generating, by the one or more processors, a combination of the uncertainty map and the customer interest map;

identifying, by the one or more processors using the combination of the uncertainty map and the customer interest map, one or more first areas having a customer interest in air quality information where the level of accuracy of the first set of outdoor air quality data is below a certain level; and

generating, by the one or more processors, a recommendation to install one or more second local sensors for one or more buildings in the one or more first areas.

16 . The method of claim 10 , further comprising:

assessing, by the one or more processors, how representative one or more locations of the one or more local sensors are of an overall outdoor air quality of the building; and

generating, by the one or more processors responsive to assessing how representative the one or more locations of the one or more local sensors are of the overall outdoor air quality of the building, a recommendation to install one or more second local sensors.

17 . One or more non-transitory storage medium storing instructions thereon that, when executed by one or more processors, cause the one or more processors to implement operations comprising:

obtaining, from a regional air quality data source, a first set of outdoor air quality data, wherein the first set of outdoor air quality data represents air quality measured for a region including a building or proximate to the building;

obtaining, from one or more local sensors coupled to or positioned proximate to the building, a second set of outdoor air quality data, wherein the second set of outdoor air quality data represents air quality measurements at one or more positions at or near an exterior of the building;

executing a model, using the first set of outdoor air quality data and the second set of outdoor air quality data as input to generate an air quality assessment for the building based at least on determining a correlation factor between the first set of outdoor air quality data and the second set of outdoor air quality data, wherein executing the model to generate the air quality assessment for the building includes:

executing the model, using at least a portion of the first set of outdoor air quality data and at least a portion of the second set of outdoor air quality data as inputs to the model, to:

determine, based on a comparison of at least the portion of the first set of outdoor air quality data and at least a portion of the second set of outdoor air quality data, a weight metric correlating at least the portion of the first set of outdoor air quality data with at least the portion of the second set of outdoor air quality data; and

generate, using the weight metric, a predicted air quality value for the building; and

wherein the model is trained using data correlating local air quality data with regional air quality data;

wherein the predicted air quality value for the building is determined relative to outdoor air quality proximate to the building; and

controlling, based at least on the air quality assessment, one or more building systems to affect the air quality within the building, by implementing one or more control actions.

18 . The one or more non-transitory storage medium of claim 17 , the operations further comprising:

obtaining, from the regional air quality data source, a plurality of future air quality values for the region including the building or proximate to the building, wherein a first future air quality value of the plurality of future air quality values corresponds to a given first point in time and a second future air quality value of the plurality of future air quality values corresponds to a given second point in time, and wherein the plurality of future air quality values are generated by a regional model;

obtaining, from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data corresponds to the given first point in time;

determining, using the first future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a localized air quality value for the building at the given first point in time; and

generating, using the second future air quality value of the plurality of future air quality values and the third set of outdoor air quality data, a second localized air quality value for the building for the given second point in time, wherein the second localized air quality value for the building is a predicted value.

19 . The one or more non-transitory storage medium of claim 17 , wherein the air quality assessment for the building includes a predicted indoor air quality value for the building for a future point in time, and the operations further comprising:

obtaining, from the regional air quality data source, a predicted outdoor air quality value for the region including the building or proximate to the building, wherein the predicted outdoor air quality value for the region is generated by a regional model and the predicted outdoor air quality value for the region pertains to the future point in time;

obtaining, from the one or more local sensors, a third set of outdoor air quality data, wherein the third set of outdoor air quality data pertains to outdoor air quality data prior to the future point in time;

updating, using at least a portion of the third set of outdoor air quality data and the predicted outdoor air quality value for the region, the predicted indoor air quality value for the building for the future point in time; and

determining, using a fourth set of outdoor air quality data, an actual air quality value for the building at the future point in time, wherein the actual air quality value for the building at the future point in time is used to update the regional model that generated the predicted outdoor air quality value for the region.