Landslide Susceptibility Prediction Considering Regional Soil Erosion Based on Machine-Learning Models

Soil erosion (SE) provides slide mass sources for landslide formation, and reflects long-term rainfall erosion destruction of landslides. Therefore, it is possible to obtain more reliable landslide susceptibility prediction results by introducing SE as a geology and hydrology-related predisposing factor. The Ningdu County of China is taken as a research area. Firstly, 446 landslides are obtained through government disaster survey reports. Secondly, the SE amount in Ningdu County is calculated and nine other conventional predisposing factors are obtained under both 30 m and 60 m grid resolutions to determine the effects of SE on landslide susceptibility prediction. Thirdly, four types of machine-learning predictors with 30 m and 60 m grid resolutions—C5.0 decision tree (C5.0 DT), logistic regression (LR), multilayer perceptron (MLP) and support vector machine (SVM)—are applied to construct the landslide susceptibility prediction models considering the SE factor as SE-C5.0 DT, SE-LR, SE-MLP and SE-SVM models; C5.0 DT, LR, MLP and SVM models with no SE are also used for comparisons. Finally, the area under receiver operating feature curve is used to verify the prediction accuracy of these models, and the relative importance of all the 10 predisposing factors is ranked. The results indicate that: (1) SE factor plays the most important role in landslide susceptibility prediction among all 10 predisposing factors under both 30 m and 60 m resolutions; (2) the SE-based models have more accurate landslide susceptibility prediction than the single models with no SE factor; (3) all the models with 30 m resolutions have higher landslide susceptibility prediction accuracy than those with 60 m resolutions; and (4) the C5.0 DT and SVM models show higher landslide susceptibility prediction performance than the MLP and LR models.

Overview on Design Considerations for Development of Disposable Microbioreactor Prototypes

Microbioreactors are a miniaturized scale bioreactor system normally designed for bioprocess development. Such a microbioreactor design offer a new platform in carrying out cheap fermentation experiments under well controlled conditions – comparable to that of typical bench scale bioreactors. Additionally, by adapting polymer technology, microbioreactor can for example be made disposable. Thus, eliminates the need for cleaning of the reactor at the end of every experiment. Since typical working volumes of microbioreactors are less than 1 mL, this furthermore reduces substrate and utility consumption per experiment. Additionally, often a microbioreactor system is interfaced with optical measurements to acquire a real-time experimental data and thus, increases the amount of information gained per experiment. To design a microbioreactor system, one must consider the design of the entire system that drives the reactor and not just restrict the design only to the mechanical aspects of the reactor. In this paper, important design considerations as well as technical challenges for establishment of a microbioreactor to facilitate a typical aerobic fermentation processes are discussed. These include reactor operating feature and size, reactor mechanics (materials, fabrications, and mixing), reactor fluidics (connections, aeration, evaporation and feeding strategy), process control of physical parameters (temperature, pH, and dissolved oxygen level) and detection methods for measuring the cells concentration. Mikrobioreaktor adalah sistem bioreaktor skala minatur yang kebiasaannya direkabentuk untuk pembangunan bioproses. Rekabentuk mikrobioreactor seperti ini memberikan pendekatan yang baru dalam menjalankan eksperimen-eksperimen fermentasi berkos rendah pada keadaan terkawal – menghampiri pada keadaan yang secara tipikalnya diperolehi di bioreaktor skala makmal. Malah, dengan mengadaptasikan teknologi polimer, mikrobioreaktor boleh dijadikan sebagai bahan pakai-buang. Secara tidak langsung ini membasmi langkah yang diperlukan untuk pembersihan reaktor di akhir setiap eksperimen. Oleh sebab isipadu kerja yang tipikal bagi mikrobioreaktor adalah kurang dari 1 mL, ini akan mengurangkan penggunaan bahan dan utiliti bagi setiap eksperimen. Sistem mikrobioreaktor juga sering dilengkapi dengan cara pengukuran optik untuk mendapatkan data-data eksperimen benar dan ini seterusnya meningkatkan maklumat-maklumat yang boleh diperolehi setiap eksperimen. Untuk merekabentuk sistem mikrobioreaktor, adalah perlu untuk menilai rekabentuk bagi keseluruhan sistem dan bukan menghadkan rekabentuk hanya pada cirri-ciri mekanikal reaktor sahaja. Dalam kertas kerja ini, dibincangkan penilaian rekabentuk yang penting dan ciri-ciri teknikal bagi penghasilan mikrobioreaktor untuk proses fermentasi aerobik. Ini termasuk saiz dan cara operasi reaktor, ciri-ciri mekanik reaktor (bahan-bahan, fabrikasi dan pengadukan), ciri-ciri bendalir reaktor (penyambungan, pengudaraan, pemeruapan dan strategi suapan), proses kawalan parameter fizikal (suhu, pH, dan oksigen terlarut) dan cara-cara untuk pengukuran kepekatan sel.