sensor data of a potential violation.

How does this evidence stack up against the enforcement record for the complaints? Citizen complaints submitted via 311 and routed to the DEP trigger an inspection, and pub-lic-record repositories made available by the city include information about how each complaint was resolved. Examining the records, we found that, for all complaints in this study, 78% resulted in a “No violation could be observed” status and only 2% in a violation ticket being issued. Figure 4b shows, in the specific case of after-hours construction noise, no violation could be observed in 89% of all cases, and none of the inspections resulted in a violation ticket being issued.

There are multiple possible explanations for the significant gap between the evidence collected by the sensor network and the results of the inspections. For example, we speculate it is due in part to the delay in the city’s response to complaints, four to five days on average, which is too great for phenomena that are both transient and traceless. Another factor is the conspicuousness of the inspection crew that alone modifies the behavior of potentially offending sources, as we observed during our site visits with the DEP. Moreover, under some circumstances the city government grants special, after-hours construction permits under the assumption of minimal noise impact, as defined by the noise code. It is thus possible that some after-hours activity results from such permits. We are currently mining after-hours-construction-permit data to understand this relationship better.

In all cases, the SONYC sensing
and analytical framework is able to
address the shortcomings of cur-
rent monitoring and enforcement
mechanisms by providing hard data
to: quantify the actual impact of af-
ter-hours construction permits on
the acoustic environment, and thus
nearby residents; provide historical
data that can validate complaints
and thus support inspection efforts
on an inconspicuous and continuous
basis; and develop novel, data-driven
strategies for the efficient alloca-
tion of inspection crews in space and
cluding crowdsourcing workers and
volunteers, and bear meaningful rela-
tionship to the properties of the data
in the physical world that, in the case
of sound, implies the need for three-
dimensional visualization.

We have been working on a three-dimensional, urban geographic information system (GIS) framework called Urbane9 (see Figure 3), an interactive tool, including a novel three-dimensional map layer, we developed from the ground up to take advantage of the GPU capabilities of modern computing systems. It allows for fast, potentially real-time computation, as well as integration and visualization of multiple data streams commonly found in major cities like New York City. In the context of SONYC, we have expanded Urbane’s capabilities to include efficient management of high-resolution temporal data. We achieve this efficiency through a novel data structure we call the “time lattice” that allows for fast retrieval, visualization, and analysis of individual and aggregate sensor data at multiple time scales (such as hours, days, weeks, and months). An example of data retrieved through this capability can be seen in Figure 3, right plot. We have since used Urbane and the time lattice to support the preliminary noise analysis we cover in the next section, but their applicability goes well beyond audio.

We are currently expanding Urbane to support visual spatiotemporal queries over noise data, including computational-topology methods for pattern detection and retrieval. Similar tools have proved useful in smart-cities research projects, including prior collaborations between team members and the New York City Department of Transportation and Taxi and Limousine Commission. 7, 10

Data-Driven Mitigation

We conducted a preliminary study in

2017 on the validity and response of
noise complaints around the Wash-
ington Square Park area of Manhattan
using SONYC’s sensing and analytics
infrastructure. 19 The study combined
information mined from the log of civ-
ic complaints made to the city over the
study period through the 311 system,
For the study we chose an area in
Greenwich Village with a relatively
dense deployment of 17 nodes. We
established a 100-meter boundary
around each node and merged them
to form the focus area. From 311,
we collected all non-duplicate noise
complaints occurring within this area
that had been routed to the DEP while
neighboring sensors were active. Note
this criterion discards complaints
about noise from residents that are
routed to the police department and
tend to dominate the 311 log; see Fig-
ure 4a for a breakdown of selected
complaint types.

Over an 11-month period—May 2016 to April 2017—51% of all noise complaints in the focus area were related to after-hours construction activity ( 6 P.M.– 7 A.M.), three times the amount in the next category. Note combining all construction-related complaints adds up to 70% of this sample, highlighting how disruptive to the lives of ordinary citizens this particular category of noise can be.

Figure 4c includes SPL values (blue line) at a five-minute resolution for the after-hours period during or immediately preceding a subset of the complaints. Dotted green lines correspond to background levels, computed as the moving average of SPL measurements within a two-hour window. Dotted black lines correspond to SPL values 10dB above the background, the threshold defined by the city’s noise code to indicate potential violations. Finally, we were able to identify events (in red) in which instantaneous SPL measurements were above the threshold. Our analysis resulted in detection of 324 such events we classified by noise source and determined 76% (246) were related to construction as follows: jackhammering (223), compressor engines ( 16), metallic banging/scraping ( 7), and the remainder to non-construction sources, mainly sirens and other traffic noise. Our analysis found for 94% of all after-hours construction complaints quantitative evidence in our