A Tested Method for Assessing and Predicting Weather-Crime Associations

Few studies have focused on haze as a weather element and its correlation with crime. In this study, we examined haze as a weather variable to investigate its effects on criminal activity. We used both monthly crime data and weather records to build a regression model to predict crime cases considering three weather factors; temperature, humidity and haze. We applied this model in two different climate provinces in Saudi Arabia, namely, Riyadh and Makkah. Riyadh is a desert area and observes haze approximately 17 days per month on average, while Makkah is a coastal area observing haze an average of 4 days per month. We found a measurable relationship between each of these three variables and criminal activity. However, haze had the most effect on theft, drug and assault crimes in Riyadh compared to the other elements. Temperature and humidity have a significant relationship with crime in Makkah, while haze had no significant influence in that region.

Pengaruh Suhu Permukaan Laut (SPL) terhadap Curah Hujan di Perairan Bali menggunakan Data Citra Satelit

Rainfall is a weather element. Sea surface temperatures (SST) affects precipitation. SST and rainfall have a high variability which can be measured by satellite. At a regional scale, a research of the effect of SST on rainfall analyzed island rainfall, which means that there is still little research on rainfall in the waters. This study purposed to find out the variability and correlation between SST and rainfall in the Bali waters. It used satellite MODIS and TRMM for 10 years, started from 2010 to 2019. The data used was SST MODIS and rainfall TRMM level 3 with the geographic coordinates boundaries area 114.4281o East - 115.7145o East, and 7.8168o South 8.9868o South. The method of this study was correlation analyzed with time lag between of SST and rainfall. The variability of SST in the Bali waters were ranged from 25,2 oC to 31,6 oC. Furthermore, the variability of rainfall was ranged from 0 mm to 556,92 mm. The changes patterns of SST and precipitation in Bali water were related to the season in each month. The data showed that the SST was warmer in the rainy season compared to the SST in the dry season. Besides, the rainfall increases when entering the rainy season, and the decreases when entering the dry season. The correlation between SST and rainfall in this waters area ranged from weak to strong. Correlation formed in the rainy season is negative with a correlation coefficient between -0.34 to -0.74. However, in the dry season there was a positive correlation with a correlation coefficient ranging from 0.77 to 0.92.

Spatiotemporal Approaches for Quality Control and Error Correction of Atmospheric Data through Machine Learning

We propose three quality control (QC) techniques using machine learning that depend on the type of input data used for training. These include QC based on time series of a single weather element, QC based on time series in conjunction with other weather elements, and QC using spatiotemporal characteristics. We performed machine learning-based QC on each weather element of atmospheric data, such as temperature, acquired from seven types of IoT sensors and applied machine learning algorithms, such as support vector regression, on data with errors to make meaningful estimates from them. By using the root mean squared error (RMSE), we evaluated the performance of the proposed techniques. As a result, the QC done in conjunction with other weather elements had 0.14% lower RMSE on average than QC conducted with only a single weather element. In the case of QC with spatiotemporal characteristic considerations, the QC done via training with AWS data showed performance with 17% lower RMSE than QC done with only raw data.

HUBUNGAN CUACA DAN KONSENTRASI PM10 (STUDI KASUS DI KOTA BANJARBARU)

This research’s aim was to identify the relationship between weather element with PM10 concentration in Banjarbaru both during normal condition and during smoke fog (smog) condition, to study the condition’s effect afflicts to weather element and PM10 concentration in ambient air and to determine standard quality concentration PM10’s threshold in ambient air during smog condition. The data were 10 minute PM10, humidity, and temperature and daily weather of 2015 that obtained from Banjarbaru Climatology Station meanwhile data of hotspot’s in South Kalimantan at 2015 was taken from MODIS satellite of Terra Aqua owned by NOAA. The 10 minutes data has been clustered using K-means method and the daily weather element relationship with PM10 concentration obtained based on regression analysis. When normal conditions, only temperature, and duration of irradiance were significantly has positively correlated with PM10 concentration, air humidity and significant rainfall are negatively correlated, the remain is not significant in effect, while during smog conditions; temperature, duration of irradiation, air pressure, average wind velocity, and maximum significant wind speed are positively correlated, air humidity, and rainfall significantly negatively correlated. Based on the results of K-means clustering analysis of PM10 concentration, there was higher humidity, higher temperature, and PM10 concentrations were below the standard quality threshold under normal conditions while in the case of smog conditions, lower humidity, lower temperature, and PM10 concentrations were above the quality standard threshold. PM10 concentration during smog condition reaches dangerous status/above the standard quality threshold before dry season until late dry season at 02.20 is in the dusk until 12.30 pm.