ForceX-AI/GeoForce-CNN-v1.1

GeoForce-CNN v1.1: Physics-Informed CNN Surrogate for Geothermal Reservoir Prediction

GeoForce is a physics-informed convolutional neural network (CNN) that predicts temperature and pressure field evolution in geothermal reservoirs. It replaces computationally expensive numerical simulators with a compact 57,802-parameter model that runs in 3.2ms on CPU — a 282,350x speedup over finite-difference simulation.

Metric	Value
Temperature RMSE	3.31°C
Temperature R²	0.994
Pressure RMSE	0.354 MPa
Pressure R²	0.997
Physics Violations	0.0%
Inference Time	3.19 ms (CPU)
Speedup vs Simulator	282,350x
Parameters	57,802

Model Description

GeoForce maps static reservoir properties (temperature, permeability, porosity, depth, well locations, pressure) directly to spatiotemporal temperature and pressure fields over a 20-year production horizon. It was designed for rapid uncertainty quantification and well placement optimization in Indonesian geothermal systems.

Architecture

Encoder-Residual-Decoder CNN:

Input (batch, 6, 32, 32)
    ↓
[Encoder]
    ConvBlock: Conv2d(6→32, 3×3) + BatchNorm + ReLU
    ConvBlock: Conv2d(32→32, 3×3) + BatchNorm + ReLU
    ↓
[Middle]
    ResidualBlock: Conv→BN→ReLU→Conv→BN + skip → ReLU
    ResidualBlock: Conv→BN→ReLU→Conv→BN + skip → ReLU
    ↓
[Decoder]
    ConvBlock: Conv2d(32→32, 3×3) + BatchNorm + ReLU
    Conv2d(32→10, 1×1) + Sigmoid
    ↓
Output (batch, 10, 32, 32)
  → Channels 0-4: Temperature at years 4, 8, 12, 16, 20
  → Channels 5-9: Pressure at years 4, 8, 12, 16, 20

Input Channels (6)

Channel	Content	Normalization
0	Initial temperature field (°C)	(T - 25) / 325
1	Log₁₀ permeability (m²)	(log_k + 16) / 4
2	Well mask (Gaussian decay)	[0, 1]
3	Base pressure (Pa)	(P - 5e6) / 20e6
4	Porosity	(φ - 0.01) / 0.14
5	Depth (m)	(z - 800) / 1700

Physics-Informed Loss

The training loss combines data-driven MSE with three physics constraints:

L_total = L_data + 0.1 × L_physics
L_physics = 0.1 × L_temporal + 0.01 × L_spatial + 0.001 × L_darcy

• Temporal smoothness: Penalizes non-physical jumps between timesteps (energy conservation proxy)
• Spatial smoothness: Discrete Laplacian penalty enforcing diffusion behavior
• Darcy coupling: Constrains pressure gradients in high-permeability zones

Training

• Data: 1,000 synthetic reservoir simulations via implicit finite-difference solver (coupled heat + Darcy flow)
• Parameter ranges: Calibrated to Indonesian geothermal fields (Kamojang, Wayang Windu, Darajat)
• Split: 800 train / 100 val / 100 test (seed=42)
• Optimizer: Adam (lr=1e-3, ReduceLROnPlateau)
• Training time: 44.9 minutes on CPU (no GPU required)
• Best epoch: 352 / 402 (early stopped, patience=50)
• Best validation loss: 0.000382

Quick Start

import torch
import numpy as np
from reservoir_cnn import ReservoirCNN

# Load model
model = ReservoirCNN(in_channels=6, n_time_steps=5, base_filters=32)
checkpoint = torch.load("geoforce_cnn_v1.1.pt", map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model_state_dict"])
model.eval()

# Prepare input: 6-channel tensor on 32×32 grid
# Example: Kamojang-like reservoir
base_temp = 245.0     # °C
log_perm = -14.0      # log10(m²)
base_pressure = 15e6  # Pa (15 MPa)
porosity = 0.08
depth = 1500.0        # m
n_wells = 3

# Normalize inputs
inp = torch.zeros(1, 6, 32, 32)
inp[0, 0] = (base_temp - 25) / 325          # Temperature
inp[0, 1] = (log_perm + 16) / 4             # Permeability
# Channel 2: well mask (place wells with Gaussian decay)
for _ in range(n_wells):
    wx, wy = np.random.randint(4, 28, size=2)
    for i in range(32):
        for j in range(32):
            d = ((i - wy)**2 + (j - wx)**2) / 50.0
            inp[0, 2, i, j] = max(inp[0, 2, i, j].item(), np.exp(-d))
inp[0, 3] = (base_pressure - 5e6) / 20e6    # Pressure
inp[0, 4] = (porosity - 0.01) / 0.14        # Porosity
inp[0, 5] = (depth - 800) / 1700            # Depth

# Run inference
with torch.no_grad():
    output = model(inp)  # (1, 10, 32, 32) normalized [0,1]

# Denormalize to physical units
temperature = output[0, :5] * 350.0          # °C, shape (5, 32, 32)
pressure = output[0, 5:] * 50e6              # Pa, shape (5, 32, 32)

print(f"Year 20 avg temperature: {temperature[4].mean():.1f}°C")
print(f"Year 20 avg pressure: {pressure[4].mean()/1e6:.2f} MPa")

Validation Results

Per-Timestep Accuracy

Year	Temp RMSE (°C)	Pressure RMSE (MPa)
4	4.025	0.356
8	3.262	0.364
12	3.333	0.326
16	3.005	0.332
20	2.811	0.390

Benchmark Comparison

Method	Temp Accuracy	Inference	Hardware
TOUGH2 (full physics)	Exact	15-30 min	CPU
USGS Brady Hot Springs ML	< 3.68% relative	0.9 s	GPU
Fourier Neural Operator	~1-3% error	~10 ms	GPU required
GeoForce v1.1	3.31°C RMSE (1.3%)	3.2 ms	CPU only

Version History

Version	Params	Temp R²	Pressure R²	Status
v1.0	56,938	0.975	-0.003	Retired (pressure prediction failed)
v1.1	57,802	0.994	0.997	Current — all thresholds pass

The v1.0 failure was caused by compressing three physical parameters (pressure, porosity, depth) into a single input channel. Each parameter now has its own dedicated channel in v1.1. Full failure analysis is documented in the technical report.

Limitations

1. 2D grid only (32×32 horizontal slice) — no vertical flow or gravity convection
2. Single-phase liquid water — no steam-water phase transitions
3. Homogeneous permeability per scenario — no fracture networks
4. Synthetic training data — not yet validated against real field measurements
5. Max error of 47.3°C in extreme edge cases near training distribution boundaries

Use Cases

• Uncertainty quantification: Run 10,000+ Monte Carlo samples in < 1 minute
• Well placement optimization: Evaluate hundreds of configurations in seconds
• Screening studies: Rapidly assess reservoir viability before committing to full simulation
• Education: Demonstrate reservoir physics concepts with instant feedback

Files

File	Description
geoforce_cnn_v1.1.pt	PyTorch checkpoint (244 KB)
reservoir_cnn.py	Model architecture (ReservoirCNN class)
validation_metrics_v1.1.json	Full validation results on 100 test samples
hyperparams.yaml	Training configuration
training_log.json	Complete training history (402 epochs)
technical-report.md	Full technical report with methodology and failure analysis

Citation

@software{geoforce2026,
  title={GeoForce: Physics-Informed CNN Surrogate for Geothermal Reservoir Prediction},
  author={Riupassa, Robi Dany},
  year={2026},
  publisher={ForceX AI},
  url={https://huggingface.co/ForceX-AI/GeoForce-CNN-v1.1},
  version={1.1.0}
}

About ForceX AI

ForceX AI builds AI-powered tools for the energy industry — geothermal, renewable, oil & gas, and nuclear. Our models are trained on real simulation data and validated against industry benchmarks.

• Platform: platform.forcex-ai.com
• Website: forcex-ai.com