In Finland, acid sulfate (AS) soils are regarded as a serious environmental threat towards the Baltic Sea and watersheds situated in land areas that have emerged from the sea since the last glaciation due to glacial isostasy. The aim of this study is to compare the behavior of coarse-grained AS soil materials to the behavior of fine-grained AS soils and coarse-grained non-AS soils in order to (1) assess the potential environmental threat of coarse-grained AS soils and (2) to assess the need to distinguish coarse-grained AS soils from fine-grained AS soils in future risk assessment of AS soils. The hypotheses are that (1) a coarser grain size enhances the rate of oxidation and pH decrease due to larger inherited pore size, enabling better initial aeration and less efficient buffering processes due to lower particle surface areas and different mineralogy (more weathering resistant quartz and feldspars), and that (2) the leaching of acid generating materials and elements from coarse grained AS soils is significantly lower as compared to fine-grained AS soils but significantly higher as compared to coarse grained non-AS soils. The study used an incubation based "let the soil speak for itself"-approach, which means that parameters such as pH, acidity, amount of elements leached, and the electric conductivity of the leachates were measured on arrays of sample aliquots before, during, and after a 16 week incubation (oxidation) period. Even though the coarse-grained AS soil materials contained one order of magnitude less sulfide than the fine-grained AS soil materials, a S mass fraction as low as 0.01%, the pH dropped well below 4.0 upon oxidation, thus being classified as AS soils. The amount of acid generating materials and elements leached from coarse-grained AS soil materials were at least one order of magnitude less, as compared to the fine-grained AS soil materials, except for Fe, which leached in similar or greater quantities from coarse-grained AS soil materials. The differences in the leaching of acid generating materials and elements suggest it would be beneficial to divide coarse-grained and fine-grained AS soils into separate subgroups for risk management purposes.
Imbalanced datasets are one of the main challenges in digital soil mapping. For these datasets, machine learning techniques commonly overestimate the majority classes and underestimate the minority ones. In general, this generates maps with poor precision and unrealistic results. Considering these maps for land use decision-making can have dire consequences. This is the case of acid sulfate (AS) soils, a type of harmful soil that can generate serious environmental damage when drained in agricultural or forestry activities. Therefore, it is necessary to create high-precision maps to avoid environmental damage. Although most soil class datasets in nature are imbalanced, this problem has hardly been studied. One of the main objectives of this work is the evaluation of different techniques to address the problem of imbalanced datasets. The methods considered to balance the dataset are an undersampling technique, the addition of more samples, and the combination of both. For increasing the number of samples from the minority class, we develop a new technique by creating artificial samples from the quaternary geological map. The method used for the modeling is Random Forest, one of the best methods for the classification of AS soils. Balancing the dataset improves the performance of the model in all the studied cases, where the values of the metrics for both classes are above 80%. The consideration of artificial non-AS soil samples improves the prediction of the model for the AS soils. Furthermore, we create AS soil probability maps for the four balanced datasets and the imbalanced dataset. The modeled AS soil probability maps created from the balanced datasets have high precision. A detailed comparison between the maps is made. The predictions of some of these maps match between 75%–80% of the study area. In addition, the extent of the AS soils obtained in all the cases is compared with the extent of the AS soils in the conventionally produced occurrence map. The good results of this study confirm the importance of balancing the dataset to improve the prediction and classification of AS soils.
Acid sulfate soils are one of the most environmentally harmful soils existing in nature. This is because they produce sulfuric acid and release metals, which may cause several ecological damages. In Finland, the occurrence of this type of soil in the coastal areas constitutes one of the major environmental problems of the country. To address this problem, it is essential to precisely locate acid sulfate soils. Thus, the creation of occurrence maps for these soils is required. Nowadays, different machine learning methods can be used following the digital soil mapping approach. The main goal of this study is the evaluation of different supervised machine learning techniques for acid sulfate soil mapping. The methods analyzed are Random Forest, Gradient Boosting and Support Vector Machine. We show that Gradient Boosting and Random Forest are suitable methods for the classification of acid sulfate soils, the resulting probability maps have high precision. However, the accuracy of the probability map created with Support Vector Machine is lower because this method overestimates the non-AS soils occurrences. We also compare these modeled probability maps with the conventionally produced occurrence map. In general, the modeled maps are more objective and accurate than the conventional maps. Moreover, the mapping process using machine learning techniques is faster and less expensive.
Acid sulfate soils can cause severe environmental harm due to a low pH and mobilization of harmful elements. Acid sulfate soil material is formed when oxidation of sulfide minerals causes a drop in pH to <4.0 for mineral oil materials and <3.0 for organic soil materials or when the soil materials contain enough sulfide to potentially do so. Two dredged, acid sulfate soil materials from Finland were used in this laboratory study. Chemical analyses were performed to determine the pre-incubation characteristics of both fresh dredged sediment samples and oxidized samples after 23 weeks of incubation. Total element concentrations were determined after digestion in aqua regia by ICP-MS or ICP-OES. The leachable concentration of elements was determined by using the two-stage shaking test (method SFS-EN 12457-3). The leaching of harmful elements (Cd, Co, Ni, Mn, and Zn) was high in the acidified dredged spoil samples. Also, the leaching of S was high. The soluble concentration was dependent on total concentration, pH, and the mobility of the elements. During a 23-week oxidation period, the impact of various amounts of industrial side streams (alkaline ashes, industrial lime residues) as neutralizing agents on the acid-generating dredged sediments was investigated in the laboratory. Calcite was used as a reference material. pH measurements were carried out during the incubation period. The leaching of elements was determined with a modified method based on the SFS-EN 12457-2 standard before and after oxidation. The untreated dredged spoils and the samples treated with too low amounts of neutralizing agents, acidified to pH < 4 during the oxidation period. Thus, harmful elements were leached out. However, the 100 % theoretical calculated neutralization need was suitable to prevent acidification and thus the leaching of harmful substances from the neutralized acid-generating dredged spoils. However, the leaching of Mo increased at neutral pH values. The results showed that industrial side streams can be applicable for the neutralization of acid sulfate soil materials. However, the legislation must also be considered.
'/%3e%3c/defs%3e%3cpath fill='%23012169' d='M0 0h10080v5040H0z'/%3e%3cpath stroke='%23fff' stroke-width='.6' d='m0 0 6 3m0-3L0 3' clip-path='url(%23b)' transform='scale(840)'/%3e%3cpath stroke='%23e4002b' stroke-width='.4' d='m0 0 6 3m0-3L0 3' clip-path='url(%23c)' transform='scale(840)'/%3e%3cpath stroke='%23fff' stroke-width='840' d='M2520 0v2520M0 1260h5040'/%3e%3cpath stroke='%23e4002b' stroke-width='504' d='M2520 0v2520M0 1260h5040'/%3e%3cg fill='%23fff'%3e%3cuse xlink:href='%23d' x='2520' y='3780'/%3e%3cuse xlink:href='%23a' x='7560' y='4200'/%3e%3cuse xlink:href='%23a' x='6300' y='2205'/%3e%3cuse xlink:href='%23a' x='7560' y='840'/%3e%3cuse xlink:href='%23a' x='8680' y='1869'/%3e%3cuse xlink:href='%23e' x='8064' y='2730'/%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath fill='%23001489' d='M0 0v6h9V0z'/%3e%3cpath fill='%23e03c31' d='M0 0v3h9V0z'/%3e%3cg stroke='%23fff' stroke-width='2'%3e%3cpath id='d' d='m0 0 4.5 3L0 6m4.5-3H9'/%3e%3cuse xlink:href='%23b' stroke='%23ffb81c' clip-path='url(%23c)'/%3e%3c/g%3e%3cuse xlink:href='%23d' fill='none' stroke='%23007749' stroke-width='1.2'/%3e%3c/g%3e%3c/svg%3e)