The response of the sensor platform is read-out in the form of the resistance across the active sensitive film of each of the 72 gas sensors integrating the sensor array; hence, each measurement produced a 72-channel time series, each of which represented by a 260-second time series collected at a sample rate of 100 samples per second (Hz), reflecting all the environmental changes in the evaluated scenario. For a more detailed analysis and discussion on the processing of the time series as well as a graphical illustration of them please refer to Sections 2 and 3 and Figure 4, respectively, of the manuscript below. For manipulation purposes, the data is organized into eleven folders, each containing the number of measurements per chemical class identity and nominal concentration indicated above and described in the Table 2 of the manuscript. For example the folder named “Toluene_200” means the name of the gas identity is Toluene, which has been dosed at 200 ppmv. Each folder contains 6 folders, each representing the line location within the test area of the wind tunnel (location 1, L1, to location 6, L6, being L1 the closest point to the gas source) from which the set of time-series were recorded. In each of these folders there are 300 files, each of which corresponding to the number of measurements recorded at each location in the tunnel. The name of each file contains the exact log information of each of the measurements performed during the entire experiment, which is organized as follows. The first 12 digits of the file name (e.g., 201106060617) indicate the date and time at which each specific measurement was collected, starting from the year, month, day, and time. The last 4 digits in the following 19 characters of the name file, (e.g., board_setPoint_500V), indicate the fixed operating temperature value, represented by a voltage value applied to the embedded heating element in the chemical sensor, applied to the entire sensing platform, which can adopt nominal values from 4 to 6 V with an resolution value of 0.5 V. Note that the value 500V in the example is a graphical representation of the 5V value applied to the sensor’s heater. For more details on the operating principles of the chemical sensors utilized in our platform please refer to Section 2 of the manuscript. The last 3 digits in the following 16 characters of the file name (e.g., fan_setPoint_060) indicates the set-point value of the nominal rotational speeds of the multiple-step motor-driven exhaust fan utilized to induce the distinct artificial airflows speed in the wind tunnel. Only three values were adopted in this condition: the value “000” in the file name, which indicates the slowest rotational speed (1500 rpm), the value “060”, indicating the mid-point rotational speed value of the fan (3900rpm), and the value “100”, which refers to the fastest induced speed of the fan, 5500 rpm. The last 14 characters of the following string of 27 characters (e.g., mfc_setPoint_Toluene_200ppm) describe the analyte identity and concentration value for each particular measurement. Thus, the just mentioned example represents the class corresponding to the chemical analyte identity “Toluene” dosed at the nominal concentration value of 200 ppm. Finally, the last 2 or 3 digits in the name (e.g., “p7”) describe the line point location at which the chemo-sensory platform was located in the wind tunnel. Note that there is a shift of two numbers in the value of this position, i.e., the value p7 in actuality represents the line location 4 illustrated in Figure 2 of the cited manuscript. For example, in 201106060617_board_setPoint_500V_fan_setPoint_060_mfc_setPoint_Toluene_200ppm_p7 the entire text line stands for a stand-alone measurement of the chemo-sensory platform located at the line location L4 and in response to 200 ppm of Toluene collected on June 06 of 2011, at 06:17 am (PST), with an operating voltage applied to the heater of 5V and a nominal rotational speed of the exhaust fan of 3900 rpm. Having described the naming configuration adopted in the generated dataset, we describe the organization of the information in each of the attached files of the dataset. The data format encloses information relevant to each measurement file, containing all the time series indicated above (9 portable modules × 8 sensors, temperature and humidity values (oC and %, respectively), exhaust fan set-point and reading values, mass flow controller set-point and actual reading values (%), and reading time (ms)), which is organized as follows: Reading time (ms) fan_set_point fan_reading* mcf1_setpoint mcf2_setpoint mcf3_setpoint mcf1_read mcf2_read mcf3_read T RH 1 board1(× 8 chemical sensors) 1 board2(× 8 chemical sensors) 1 .... 1 board9(× 8 chemical sensors) where: “Reading time (ms)” is the time step for each recording (in ms, at a sample rate of 100 Hz), “fan_set_point” and “fan_reading”, is the set-point and actual reading of the exhaust fan, respectively, “mcf1_setpoint” to “mcf3_setpoint” are the opening degree set-point values given to the mass flow controllers 1 to 3 during the experiment, respectively, “mcf1_read” to “mcf1_read” are the measured opening degree of mass flow controllers 1 to 3, respectively, “T” and “R” are the temperature and relative humidity values (in oC and %, respectively) during the entire experiment, and “board1(× 8 chemical sensors)” to “board9(× 8 chemical sensors)” are the 72 time series collected as a function of time from the 8 gas sensors (in KΩ) integrating modules 1 to 9 in each location, respectively, each separated by the number “1” that stands as indicator label, forming thus the 72 time-series chemical sensor responses that is fetched to the classifier for training as described in the study. Note that there is a blank space between and among each column in the dataset. Thus, for example, in line1: 22250 0 0 100 100 100 103 103 105 22.22 63.43 1 476 555 803 497 775 885 873 843 1 346 545 635 616 571 552 773 745 1 397 509 660 638 755 744 745 657 1 420 510 525 531 504 650 719 715 1 2201 449 652 1228 847 654 850 737 1 370 459 650 445 756 773 847 803 1 345 457 587 554 757 704 769 818 1 354 407 499 696 786 686 757 733 1 339 418 547 567 653 573 773 84 The number “22250” stands for the recording made at time 22.25s, the following two numbers stand for the set-point and measured value of the fan speed, the following 6 numbers indicate the set-point (in this case, 100) and actual measured values of the MFC (103, 103, 105), the numbers “22.22” and “63.43” stand for the temperature and humidity values at that specific time recording, whereas the remaining 80 columns list the actual time series values for each measurement recording organized as described above, and in which the number “1” indicates the boundary between each sensor module board. The first and ninth boards correspond to the positions closer to the walls, whereas the board 5 is located in the main line orthogonal to the gas plume. For the exact location of each board, please refer to Figure 2 of the mentioned Journal article. *: we found out that the exhaust fan actual reading value registered on each file is not completely accurate, showing a “0” or other random values for some of the measurement recordings. Please discard this information value and utilize only the set point information for processing purposes; The value is accurate. Finally, to make the results presented in the associated article reproducible for the user of this read-me file, please use the hyper-parameter values described in the manuscript for the training task.