The migration of formation water plays a crucial role
in hydrocarbon
accumulation and preservation. The hydrodynamic field controls the
content of various ions in formation water and is an important participant
in hydrocarbon evolution. One potential high-yield gas field is the
tight sandstone gas reservoirs in the northern Tianhuan Depression
of the Ordos Basin, China. However, due to the complex gas–water
relationship and limited water sample data, the development of gas
reservoirs has encountered great difficulties; we thus analyzed the
geochemical characteristics of a large scale of formation water acquired
from the Permian in the Ordos Basin (60 water samples collected from
45 wells in the He8 Member). The results showed that formation water
is the original sedimentary water in tight sandstone reservoirs, which
represent a closed hydrological environment, which is conducive to
gas accumulation. This is also related to the demonstrated strong
water–rock reaction and diagenetic. We also developed a statistical
model between these geochemical parameters and gas preservation based
on machine learning algorithms (decision trees). Note that machine
learning, as a data-driven artificial intelligence algorithm, generates
massive correlation models that can learn from the structured training
data sets to carry out predictions or evaluations in newly presented
data. This algorithm can process large amounts of information data
more quickly and can build more perfect correlation models through
deep learning mechanisms than traditional statistical methods. The
results suggest that the metamorphism coefficient has the best indication
effect on the preservation of gas reservoirs. The hydrological environment
with (Cl–-Na+)/Mg2+ > 50.066,
Na+/Cl– ≤ 0.476, and Ma2+/Ca2+ ≤ 0.102 is a good hydrocarbon accumulation
area. This study can be applied, by analogy, to more comprehensively
interpret the correlation between the geochemical characteristics
of formation water and hydrocarbon storage and to improve the accuracy
of predicting favorable hydrocarbon accumulation areas in tight sandstone
gas reservoirs.