The reservoir characterization aims to provide the analysis and quantification of the injection-production relationship, which is the fundamental work for production management. The connectivity between injectors and producers is dominated by geological properties, especially permeability. However, the permeability parameters are very heterogenous in oil reservoirs, and expensive to collect by well logging. The commercial simulators enable to get accurate simulation but require sufficient geological properties and consume excessive computation resources. In contrast, the data-driven models (physical models and machine learning models) are developed on the observed dynamic data, such as the rate and pressure data of the injectors and producers, constructing the connectivity relationship and forecasting the productivity by a series of nonlinear mappings or the control of specific physical principles. While, due to the “black box” feature of machine learning approaches, and the constraints and assumptions of physical models, the data-driven methods often face the challenges of poor interpretability and generalizability and the limited application scopes. To solve these issues, integrating the physical principle of the waterflooding process (material balance equation) with an artificial neural network (ANN), a knowledge interaction neural network (KINN) is proposed. KINN consists of three transparent modules with explicit physical significance, and different modules are joined together via the material balance equation and work cooperatively to approximate the waterflooding process. In addition, a gate function is proposed to distinguish the dominant flowing channels from weak connecting ones by their sparsity, and thus the inter-well connectivity can be indicated directly by the model parameters. Combining the strong nonlinear mapping ability with the guidance of physical knowledge, the interpretability of KINN is fully enhanced, and the prediction accuracy on the well productivity is improved. The effectiveness of KINN is proved by comparing its performance with the canonical ANN, on the inter-well connectivity analysis and productivity forecast tasks of three synthetic reservoir experiments. Meanwhile, the robustness of KINN is revealed by the sensitivity analysis on measurement noises and wells shut-in cases.

The largest marine carbonate oilfield and gas condensate field in China have been found in the Ordovician limestones in the central Tarim Basin. They are defined as large “layered” reef-shoal and karstic reservoirs. However, low and/or unstable oil/gas production has been a big challenge for effective exploitation in ultra-deep (>6000 m) reservoirs for more than 20 years. Together with the static and dynamic reservoir data, we have a review of the unconventional characteristics of the oil/gas fields in that: (1) the large area tight matrix reservoir (porosity less than 5%, permeability less than 0.2 mD) superimposed with localized fracture-cave reservoir (porosity > 5%, permeability > 2 mD); (2) complicated fluid distribution and unstable production without uniform oil/gas/water interface in an oil/gas field; (3) about 30% wells in fractured reservoirs support more than 80% production; (4) high production decline rate is over 20% per year with low recovery ratio. These data suggest that the “sweet spot” of the fractured reservoir rather than the matrix reservoir is the major drilling target for ultra-deep reservoir development. In the ultra-deep pre-Mesozoic reservoirs, further advances in horizontal drilling and large multiple fracturing techniques are needed for the economic exploitation of the matrix reservoirs, and seismic quantitative descriptions and horizontal drilling techniques across the fault zones are needed for oil/gas efficient development from the deeply fractured reservoirs.

Waterflooding reservoir interwell connectivity characterization is the fundamental work in oil development, aiming to inverse the vital connecting channels between injectors and producers. In this paper, we endow an artificial neural network (ANN) with strong interpretability through the ordinary differential equation (ODE) of the material balance equation, proposing a physical knowledge fusion neural network (PKFNN). In addition, the proposed model could inherit the knowledge learned from different injector–producer pairs, fully improving the training efficiency. In this way, PKFNN combines the merits of both physical and machine learning approaches. Firstly, based on the physical control law and the ODE of the material balance equation, we endow the model with highly transparent modular architectures in the framework of feedforward neural network. In this way, our work has both high interpretability and excellent approximation ability, combining the merits of the physical and machine learning approaches. The proposed model shows great performance on productivity forecast and interwell connectivity reflection in several reservoir experiments. PKFNN provides a novel way to enhance the interpretability and robustness of the data-driven-based interwell connectivity-analyzing models by integrating the physical knowledge of waterflooding reservoirs.

The largest carbonate condensate field in China has been found in the central Tarim Basin. Ordovician carbonate reservoirs are generally attributed to reef-shoal microfacies along a platform margin. However, recent production success has been achieved along the NE-trending strike-slip fault zones that intersect at the platform margin. For this contribution, we analyzed the strike-slip fault effects on the reef-shoal reservoirs by using new geological, geophysical, and production data. Seismic data shows that some NE-trending strike-slip faults intersected the NW-trending platform margin in multiple segments. The research indicated that the development of strike-slip faults has affected prepositional landforms and the subsequent segmentation of varied microfacies along the platform margin. In addition, the strike-slip fault compartmentalized the reef-shoal reservoirs into multiple segments along the extent of the platform margin. We show that fractured reef-shoal complexes are favorable for the development of dissolution porosity along strike-slip fault damage zones. In the tight matrix reservoirs (porosity < 6%, permeability < 0.5 mD), the porosity and permeability could be increased by more than 2–5 times and to 1–2 orders of magnitude in the fault damage zone, respectively. This suggests that high production wells are correlated with “sweet spots” of fractured reservoirs along the strike-slip fault damage zones, and that the fractured reservoirs in the proximity of strike-slip fault activity might be a major target for commercial exploitation of the deep Ordovician tight carbonates.

N₂ huff-n-puff has proven to be a promising technique to further improve oil recovery in naturally fractured-cavity carbonate reservoirs. The effect of enhanced oil recovery (EOR) by N₂ huff-n-puff is significantly affected by various dynamic and static factors such as type of reservoir space, reservoir connectivity, water influx, operational parameters, and so on, typically leading to a significant increase in oil production. To reduce the prediction uncertainty of EOR performance by N₂ huff-n-puff, an adaptive hybrid model was proposed based on the fundamental principles of fuzzy neural network (FNN) and fractional differential simulation (FDS); a detailed prediction process of the hybrid model was also illustrated. The accuracy of the proposed FNN-FDS hybrid model was validated using production history of N₂ huff-n-puff in a typical fractured-cavity carbonate reservoir. The proposed model was also employed to predict the EOR performance by N₂ huff-n-puff in a naturally fractured-cavity carbonate reservoir. The methodology can serve as an effective tool to optimize developmental design schemes when using N₂ huff-n-puff to tap more remaining oil in similar types of carbonate reservoirs.