Today, seepage control in tailings dams has become an important problem due to the increased production in mining sites. Although very techniques have been developed to solve this problem, research in this field continues. The reason for this is that there is an ongoing search for a one hundred percent successful method to prevent seepage. In this study, the geochemical and geomechanical properties of paste material stored by the surface paste disposal (SPD) method were investigated by pilot field tests. To determine the effects of cement and pozzolanic materials on the geochemical and geomechanical properties of the paste, 2 different pilot-scale storage designs were observed for about 1 year, with no additives (reference) and binder added to some layers (cement and fly ash). Based on the data derived from the former laboratory investigations and with no additives and with a few layers of cement and fly ash, the two different designs were applied on a pilot scale near the existing tailings dam of a currently active mining enterprise. These designs were observed in inland conditions for about 1 year to determine the effects of seasonal changes on the material. The seepage analysis, surface crack densities, microstructural properties, consolidation, and cohesion values of these designs, which are directly exposed to atmospheric effects, were determined during the study period. According to the results obtained, the use of cement improved the volume compressibility coefficient of the material by approximately 25% compared to the reference design. However, the use of fly ash alongside cement improved the volume compressibility coefficient by about 75%. In conclusion, the use of cement made the material more resistant to external factors, and the usability of fly ash, which was used at a 50% replacement ratio with cement to bring down the cost, for long-time storage in the industry was demonstrated within the scope of the study.

In cemented paste backfill (CPB), fly ash (FA) can reduce cement costs. However, the chemical compositions of FA and tailings used in the CPB can vary significantly, affecting the strength values of CPBs, which can be determined through laboratory tests and play a crucial role in design operations. Therefore, developing a predictive model would be advantageous in terms of time and cost. The most critical aspect of this study is that machine learning (ML) models demonstrate high accuracy in the performance of strength prediction in experimental studies, especially in nonlinear and complex data structures, and even in the presence of uncertainty in geochemical and geophysical parameters. Among the ML algorithms, random forest (RF), artificial neural network (ANN), linear regression (LR), voting, and extreme gradient boosting (XGBoost) algorithms were used in this study. According to the results obtained, the XGBoost model exhibited the most robust predictive performance, evidenced by the highest correlation coefficient (R) (0.922) and the lowest mean absolute error (0.666). XGBoost also demonstrated its durability and stability by achieving the lowest relative absolute error (18.81%) and root mean square error (41.10%). Therefore, it has been understood that significant time and resource savings can be achieved in important projects by eliminating the need for experimental tests.

Alkali-silica reaction (ASR) can cause serious cracking in concrete. The best method in order to avoid the occurrence of ASR is the non-use of reactive aggregate in concrete production. However, reactive aggregates in quarries must be used for the sustainable usage of resources. Therefore, a more practical approach is to identify the optimal blending of such aggregates, which can be achieved through the use of the Design of Experiment-Mixture Design Method (DOE-MD). In this study, empirical approaches that can be used for ASR estimation are suggested using DOE-MD in a quarry that produces concrete aggregate and has reactive and nonreactive aggregate resources in terms of ASR and by determining aggregate mixing ratios that do not create risk in terms of ASR. The quarry in question has three different regions, which are in terms of the type of aggregate available. As a result, the aggregate from Region 2 should be used at 19 % (Region 3: 81 %) in the mixture with aggregate from Region 3. The aggregate from Region 1 should not be mixed with the aggregate from Region 2 and should be used at most at 14 % (Region 3: 86 %) in the mixture with the aggregate from Region 3.